< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1417 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')

Text #0

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.9251. Min Act: -0.1700

Data Index: 7717955 (Open Web Text)

Max Activating Token Index: 905

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.8887. Min Act: -0.1700

Data Index: 6340519 (Open Web Text)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.7252. Min Act: -0.1700

Data Index: 4667292 (Open Web Text)

Max Activating Token Index: 201

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.7147. Min Act: -0.1700

Data Index: 3357290 (Open Web Text)

Max Activating Token Index: 879

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.6450. Min Act: -0.1700

Data Index: 7447358 (Open Web Text)

Max Activating Token Index: 920

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.6248. Min Act: -0.1700

Data Index: 7447355 (Open Web Text)

Max Activating Token Index: 579

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.6120. Min Act: -0.1700

Data Index: 1591054 (Open Web Text)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.5987. Min Act: -0.1700

Data Index: 296189 (Open Web Text)

Max Activating Token Index: 622

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.6244. Min Act: -0.1700

Data Index: 4626368 (Open Web Text)

Max Activating Token Index: 568

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.6123. Min Act: -0.1700

Data Index: 4023600 (Open Web Text)

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.5836. Min Act: -0.1700

Data Index: 6760642 (Open Web Text)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.6074. Min Act: -0.1700

Data Index: 2904885 (Open Web Text)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.5806. Min Act: -0.1700

Data Index: 1303279 (Open Web Text)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.5695. Min Act: -0.1700

Data Index: 3129771 (Open Web Text)

Max Activating Token Index: 286

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.5745. Min Act: -0.1700

Data Index: 1349414 (Open Web Text)

Max Activating Token Index: 391

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.5582. Min Act: -0.1700

Data Index: 2991521 (Open Web Text)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.5638. Min Act: -0.1700

Data Index: 6026758 (Open Web Text)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.5638. Min Act: -0.1700

Data Index: 6026735 (Open Web Text)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.5437. Min Act: -0.1700

Data Index: 2364830 (Open Web Text)

Max Activating Token Index: 793

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9251. Min Range: -2.9251

Max Act: 2.5492. Min Act: -0.1700

Data Index: 7653442 (Open Web Text)

Max Activating Token Index: 602

Click toggle to see full text

Truncated

Full Text #19