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

Dataset: Open Web Text

Neuron 2797 in Layer 1

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: 4.1523. Min Range: -4.1523

Max Act: 4.1380. Min Act: -0.1700

Data Index: 5658269 (Open Web Text)

Max Activating Token Index: 355

Text #1

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.1523. Min Act: -0.1700

Data Index: 2108337 (Open Web Text)

Max Activating Token Index: 287

Text #2

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.1059. Min Act: -0.1700

Data Index: 4575119 (Open Web Text)

Max Activating Token Index: 404

Text #3

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.1231. Min Act: -0.1700

Data Index: 4417419 (Open Web Text)

Max Activating Token Index: 126

Text #4

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.1006. Min Act: -0.1700

Data Index: 4788139 (Open Web Text)

Max Activating Token Index: 728

Text #5

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.0706. Min Act: -0.1700

Data Index: 2594337 (Open Web Text)

Max Activating Token Index: 479

Text #6

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.0727. Min Act: -0.1700

Data Index: 3223193 (Open Web Text)

Max Activating Token Index: 432

Text #7

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.0796. Min Act: -0.1700

Data Index: 867315 (Open Web Text)

Max Activating Token Index: 636

Text #8

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.0737. Min Act: -0.1700

Data Index: 7133627 (Open Web Text)

Max Activating Token Index: 364

Text #9

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.0434. Min Act: -0.1700

Data Index: 6537209 (Open Web Text)

Max Activating Token Index: 819

Text #10

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.0531. Min Act: -0.1700

Data Index: 7794523 (Open Web Text)

Max Activating Token Index: 927

Text #11

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.0617. Min Act: -0.1700

Data Index: 7171699 (Open Web Text)

Max Activating Token Index: 678

Text #12

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.0608. Min Act: -0.1700

Data Index: 3470423 (Open Web Text)

Max Activating Token Index: 877

Text #13

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.0494. Min Act: -0.1700

Data Index: 113796 (Open Web Text)

Max Activating Token Index: 590

Text #14

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.0683. Min Act: -0.1700

Data Index: 3259717 (Open Web Text)

Max Activating Token Index: 374

Text #15

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.0497. Min Act: -0.1700

Data Index: 2341858 (Open Web Text)

Max Activating Token Index: 489

Text #16

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.0568. Min Act: -0.1700

Data Index: 2120122 (Open Web Text)

Max Activating Token Index: 508

Text #17

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.0171. Min Act: -0.1700

Data Index: 2054459 (Open Web Text)

Max Activating Token Index: 564

Text #18

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.0231. Min Act: -0.1700

Data Index: 4462065 (Open Web Text)

Max Activating Token Index: 519

Text #19

Max Range: 4.1523. Min Range: -4.1523

Max Act: 4.0312. Min Act: -0.1700

Data Index: 4502542 (Open Web Text)

Max Activating Token Index: 769