< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 589 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: 2.7316. Min Range: -2.7316

Max Act: 2.7316. Min Act: -0.1700

Data Index: 4834226 (Open Web Text)

Max Activating Token Index: 734

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.7023. Min Act: -0.1700

Data Index: 2856563 (Open Web Text)

Max Activating Token Index: 435

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.6980. Min Act: -0.1700

Data Index: 7561766 (Open Web Text)

Max Activating Token Index: 649

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.7148. Min Act: -0.1700

Data Index: 2148399 (Open Web Text)

Max Activating Token Index: 238

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.7094. Min Act: -0.1700

Data Index: 4864904 (Open Web Text)

Max Activating Token Index: 637

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.6995. Min Act: -0.1700

Data Index: 2791444 (Open Web Text)

Max Activating Token Index: 803

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.6835. Min Act: -0.1700

Data Index: 169108 (Open Web Text)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.6678. Min Act: -0.1700

Data Index: 6424693 (Open Web Text)

Max Activating Token Index: 525

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.6702. Min Act: -0.1700

Data Index: 8737597 (Open Web Text)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.6573. Min Act: -0.1700

Data Index: 7551339 (Open Web Text)

Max Activating Token Index: 600

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.6519. Min Act: -0.1700

Data Index: 1380582 (Open Web Text)

Max Activating Token Index: 212

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.6396. Min Act: -0.1700

Data Index: 98166 (Open Web Text)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.6449. Min Act: -0.1700

Data Index: 8174153 (Open Web Text)

Max Activating Token Index: 704

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.6298. Min Act: -0.1700

Data Index: 2480997 (Open Web Text)

Max Activating Token Index: 745

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.6197. Min Act: -0.1700

Data Index: 8414083 (Open Web Text)

Max Activating Token Index: 487

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.6303. Min Act: -0.1700

Data Index: 7766451 (Open Web Text)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.6276. Min Act: -0.1700

Data Index: 3472969 (Open Web Text)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.6481. Min Act: -0.1700

Data Index: 1212710 (Open Web Text)

Max Activating Token Index: 400

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.6211. Min Act: -0.1700

Data Index: 784303 (Open Web Text)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.7316. Min Range: -2.7316

Max Act: 2.5985. Min Act: -0.1700

Data Index: 2924272 (Open Web Text)

Max Activating Token Index: 511

Click toggle to see full text

Truncated

Full Text #19