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

Dataset: Open Web Text

Neuron 1217 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.3739. Min Act: -0.1700

Data Index: 735509 (Open Web Text)

Max Activating Token Index: 910

Text #1

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.3251. Min Act: -0.1700

Data Index: 2067244 (Open Web Text)

Max Activating Token Index: 530

Text #2

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.2996. Min Act: -0.1700

Data Index: 1522564 (Open Web Text)

Max Activating Token Index: 358

Text #3

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.3005. Min Act: -0.1700

Data Index: 7169577 (Open Web Text)

Max Activating Token Index: 803

Text #4

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.2483. Min Act: -0.1700

Data Index: 3711132 (Open Web Text)

Max Activating Token Index: 797

Text #5

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.2382. Min Act: -0.1700

Data Index: 6752764 (Open Web Text)

Max Activating Token Index: 635

Text #6

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.2046. Min Act: -0.1700

Data Index: 5552729 (Open Web Text)

Max Activating Token Index: 342

Text #7

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.2325. Min Act: -0.1700

Data Index: 4327670 (Open Web Text)

Max Activating Token Index: 290

Text #8

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.1833. Min Act: -0.1700

Data Index: 1728497 (Open Web Text)

Max Activating Token Index: 408

Text #9

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.1944. Min Act: -0.1700

Data Index: 834285 (Open Web Text)

Max Activating Token Index: 848

Text #10

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.1847. Min Act: -0.1700

Data Index: 5020077 (Open Web Text)

Max Activating Token Index: 394

Text #11

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.1640. Min Act: -0.1700

Data Index: 2539082 (Open Web Text)

Max Activating Token Index: 182

Text #12

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.1519. Min Act: -0.1700

Data Index: 1170599 (Open Web Text)

Max Activating Token Index: 692

Text #13

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.1155. Min Act: -0.1700

Data Index: 735510 (Open Web Text)

Max Activating Token Index: 526

Text #14

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.1401. Min Act: -0.1700

Data Index: 1170598 (Open Web Text)

Max Activating Token Index: 371

Text #15

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.1408. Min Act: -0.1700

Data Index: 3039394 (Open Web Text)

Max Activating Token Index: 782

Text #16

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.1495. Min Act: -0.1700

Data Index: 849707 (Open Web Text)

Max Activating Token Index: 436

Text #17

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.1543. Min Act: -0.1700

Data Index: 2086045 (Open Web Text)

Max Activating Token Index: 429

Text #18

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.1215. Min Act: -0.1700

Data Index: 6278600 (Open Web Text)

Max Activating Token Index: 296

Text #19

Max Range: 4.3739. Min Range: -4.3739

Max Act: 4.1226. Min Act: -0.1700

Data Index: 3039395 (Open Web Text)

Max Activating Token Index: 53