< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 411 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: 2.8495. Min Range: -2.8495

Max Act: 2.8495. Min Act: -0.1700

Data Index: 6596060 (Open Web Text)

Max Activating Token Index: 858

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.7864. Min Act: -0.1700

Data Index: 1009452 (Open Web Text)

Max Activating Token Index: 645

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.7166. Min Act: -0.1700

Data Index: 2407234 (Open Web Text)

Max Activating Token Index: 804

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.7044. Min Act: -0.1700

Data Index: 3668013 (Open Web Text)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.6966. Min Act: -0.1700

Data Index: 959474 (Open Web Text)

Max Activating Token Index: 571

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.6949. Min Act: -0.1700

Data Index: 3044573 (Open Web Text)

Max Activating Token Index: 449

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.6393. Min Act: -0.1700

Data Index: 2810081 (Open Web Text)

Max Activating Token Index: 951

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.6588. Min Act: -0.1700

Data Index: 1239537 (Open Web Text)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.6588. Min Act: -0.1700

Data Index: 4220656 (Open Web Text)

Max Activating Token Index: 639

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.6607. Min Act: -0.1700

Data Index: 182061 (Open Web Text)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.6340. Min Act: -0.1700

Data Index: 5711552 (Open Web Text)

Max Activating Token Index: 305

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.6483. Min Act: -0.1700

Data Index: 7704893 (Open Web Text)

Max Activating Token Index: 925

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.6401. Min Act: -0.1700

Data Index: 4621891 (Open Web Text)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.6206. Min Act: -0.1700

Data Index: 3404201 (Open Web Text)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.6203. Min Act: -0.1700

Data Index: 6292170 (Open Web Text)

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.6288. Min Act: -0.1700

Data Index: 6475207 (Open Web Text)

Max Activating Token Index: 254

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.5961. Min Act: -0.1700

Data Index: 1349891 (Open Web Text)

Max Activating Token Index: 544

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.6061. Min Act: -0.1700

Data Index: 353606 (Open Web Text)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.6017. Min Act: -0.1700

Data Index: 2381497 (Open Web Text)

Max Activating Token Index: 310

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8495. Min Range: -2.8495

Max Act: 2.6149. Min Act: -0.1700

Data Index: 352023 (Open Web Text)

Max Activating Token Index: 281

Click toggle to see full text

Truncated

Full Text #19