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

Dataset: Open Web Text

Neuron 2347 in Layer 3

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: 4.2442. Min Range: -4.2442

Max Act: 4.2442. Min Act: -0.1700

Data Index: 5569613 (Open Web Text)

Max Activating Token Index: 427

Text #1

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.1485. Min Act: -0.1700

Data Index: 1992155 (Open Web Text)

Max Activating Token Index: 372

Text #2

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.1696. Min Act: -0.1700

Data Index: 7219204 (Open Web Text)

Max Activating Token Index: 899

Text #3

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.1062. Min Act: -0.1700

Data Index: 8413635 (Open Web Text)

Max Activating Token Index: 371

Text #4

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.1087. Min Act: -0.1700

Data Index: 609702 (Open Web Text)

Max Activating Token Index: 153

Text #5

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.1148. Min Act: -0.1700

Data Index: 2185740 (Open Web Text)

Max Activating Token Index: 686

Text #6

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.1137. Min Act: -0.1700

Data Index: 7669144 (Open Web Text)

Max Activating Token Index: 884

Text #7

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.0533. Min Act: -0.1700

Data Index: 2458257 (Open Web Text)

Max Activating Token Index: 692

Text #8

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.0228. Min Act: -0.1700

Data Index: 7478774 (Open Web Text)

Max Activating Token Index: 563

Text #9

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.0404. Min Act: -0.1700

Data Index: 4177586 (Open Web Text)

Max Activating Token Index: 835

Text #10

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.0383. Min Act: -0.1700

Data Index: 8022082 (Open Web Text)

Max Activating Token Index: 357

Text #11

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.0528. Min Act: -0.1700

Data Index: 7822830 (Open Web Text)

Max Activating Token Index: 809

Text #12

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.0584. Min Act: -0.1700

Data Index: 189401 (Open Web Text)

Max Activating Token Index: 508

Text #13

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.0378. Min Act: -0.1700

Data Index: 426078 (Open Web Text)

Max Activating Token Index: 384

Text #14

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.0482. Min Act: -0.1700

Data Index: 97290 (Open Web Text)

Max Activating Token Index: 391

Text #15

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.0490. Min Act: -0.1700

Data Index: 2182650 (Open Web Text)

Max Activating Token Index: 471

Text #16

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.0411. Min Act: -0.1700

Data Index: 3259709 (Open Web Text)

Max Activating Token Index: 244

Text #17

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.0585. Min Act: -0.1700

Data Index: 6328958 (Open Web Text)

Max Activating Token Index: 619

Text #18

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.0359. Min Act: -0.1700

Data Index: 3111866 (Open Web Text)

Max Activating Token Index: 516

Text #19

Max Range: 4.2442. Min Range: -4.2442

Max Act: 4.0583. Min Act: -0.1700

Data Index: 2905591 (Open Web Text)

Max Activating Token Index: 287