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

Dataset: Open Web Text

Neuron 686 in Layer 4

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: 4.4437. Min Range: -4.4437

Max Act: 4.4437. Min Act: -0.1700

Data Index: 8664352 (Open Web Text)

Max Activating Token Index: 701

Text #1

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.3091. Min Act: -0.1700

Data Index: 4154623 (Open Web Text)

Max Activating Token Index: 320

Text #2

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.2829. Min Act: -0.1700

Data Index: 7433008 (Open Web Text)

Max Activating Token Index: 563

Text #3

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.3262. Min Act: -0.1700

Data Index: 6186280 (Open Web Text)

Max Activating Token Index: 607

Text #4

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.2135. Min Act: -0.1700

Data Index: 2702904 (Open Web Text)

Max Activating Token Index: 498

Text #5

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.1741. Min Act: -0.1700

Data Index: 6236728 (Open Web Text)

Max Activating Token Index: 205

Text #6

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.1791. Min Act: -0.1700

Data Index: 5195869 (Open Web Text)

Max Activating Token Index: 733

Text #7

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.2304. Min Act: -0.1700

Data Index: 342768 (Open Web Text)

Max Activating Token Index: 439

Text #8

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.1476. Min Act: -0.1700

Data Index: 3129437 (Open Web Text)

Max Activating Token Index: 300

Text #9

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.1780. Min Act: -0.1700

Data Index: 4088689 (Open Web Text)

Max Activating Token Index: 252

Text #10

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.1341. Min Act: -0.1700

Data Index: 4484024 (Open Web Text)

Max Activating Token Index: 999

Text #11

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.1375. Min Act: -0.1700

Data Index: 7262418 (Open Web Text)

Max Activating Token Index: 758

Text #12

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.1234. Min Act: -0.1700

Data Index: 6544781 (Open Web Text)

Max Activating Token Index: 200

Text #13

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.1208. Min Act: -0.1700

Data Index: 3826127 (Open Web Text)

Max Activating Token Index: 444

Text #14

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.1220. Min Act: -0.1700

Data Index: 5186694 (Open Web Text)

Max Activating Token Index: 897

Text #15

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.1109. Min Act: -0.1700

Data Index: 4701578 (Open Web Text)

Max Activating Token Index: 739

Text #16

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.1128. Min Act: -0.1700

Data Index: 4428747 (Open Web Text)

Max Activating Token Index: 419

Text #17

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.1225. Min Act: -0.1700

Data Index: 4747772 (Open Web Text)

Max Activating Token Index: 317

Text #18

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.0895. Min Act: -0.1700

Data Index: 3035711 (Open Web Text)

Max Activating Token Index: 28

Text #19

Max Range: 4.4437. Min Range: -4.4437

Max Act: 4.1160. Min Act: -0.1700

Data Index: 1037278 (Open Web Text)

Max Activating Token Index: 890