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

Dataset: Open Web Text

Neuron 1007 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: 4.1507. Min Range: -4.1507

Max Act: 4.1507. Min Act: -0.1700

Data Index: 2022235 (Open Web Text)

Max Activating Token Index: 901

Text #1

Max Range: 4.1507. Min Range: -4.1507

Max Act: 4.1059. Min Act: -0.1700

Data Index: 5221885 (Open Web Text)

Max Activating Token Index: 517

Text #2

Max Range: 4.1507. Min Range: -4.1507

Max Act: 4.0771. Min Act: -0.1700

Data Index: 6499199 (Open Web Text)

Max Activating Token Index: 309

Text #3

Max Range: 4.1507. Min Range: -4.1507

Max Act: 4.0666. Min Act: -0.1700

Data Index: 3468105 (Open Web Text)

Max Activating Token Index: 232

Text #4

Max Range: 4.1507. Min Range: -4.1507

Max Act: 4.0494. Min Act: -0.1700

Data Index: 5576608 (Open Web Text)

Max Activating Token Index: 990

Text #5

Max Range: 4.1507. Min Range: -4.1507

Max Act: 4.0634. Min Act: -0.1700

Data Index: 256105 (Open Web Text)

Max Activating Token Index: 348

Text #6

Max Range: 4.1507. Min Range: -4.1507

Max Act: 4.0115. Min Act: -0.1700

Data Index: 8041690 (Open Web Text)

Max Activating Token Index: 642

Text #7

Max Range: 4.1507. Min Range: -4.1507

Max Act: 3.9889. Min Act: -0.1700

Data Index: 6741299 (Open Web Text)

Max Activating Token Index: 606

Text #8

Max Range: 4.1507. Min Range: -4.1507

Max Act: 3.9927. Min Act: -0.1700

Data Index: 3562516 (Open Web Text)

Max Activating Token Index: 352

Text #9

Max Range: 4.1507. Min Range: -4.1507

Max Act: 4.0024. Min Act: -0.1700

Data Index: 2068363 (Open Web Text)

Max Activating Token Index: 936

Text #10

Max Range: 4.1507. Min Range: -4.1507

Max Act: 3.9462. Min Act: -0.1700

Data Index: 6028785 (Open Web Text)

Max Activating Token Index: 1022

Text #11

Max Range: 4.1507. Min Range: -4.1507

Max Act: 3.9523. Min Act: -0.1700

Data Index: 6598176 (Open Web Text)

Max Activating Token Index: 182

Text #12

Max Range: 4.1507. Min Range: -4.1507

Max Act: 3.9510. Min Act: -0.1700

Data Index: 5956931 (Open Web Text)

Max Activating Token Index: 769

Text #13

Max Range: 4.1507. Min Range: -4.1507

Max Act: 3.9419. Min Act: -0.1700

Data Index: 7249805 (Open Web Text)

Max Activating Token Index: 786

Text #14

Max Range: 4.1507. Min Range: -4.1507

Max Act: 3.9318. Min Act: -0.1700

Data Index: 4585029 (Open Web Text)

Max Activating Token Index: 221

Text #15

Max Range: 4.1507. Min Range: -4.1507

Max Act: 3.9167. Min Act: -0.1700

Data Index: 2747236 (Open Web Text)

Max Activating Token Index: 1005

Text #16

Max Range: 4.1507. Min Range: -4.1507

Max Act: 3.8791. Min Act: -0.1700

Data Index: 1324413 (Open Web Text)

Max Activating Token Index: 428

Text #17

Max Range: 4.1507. Min Range: -4.1507

Max Act: 3.9400. Min Act: -0.1700

Data Index: 6538055 (Open Web Text)

Max Activating Token Index: 410

Text #18

Max Range: 4.1507. Min Range: -4.1507

Max Act: 3.9334. Min Act: -0.1700

Data Index: 6131298 (Open Web Text)

Max Activating Token Index: 416

Text #19

Max Range: 4.1507. Min Range: -4.1507

Max Act: 3.9237. Min Act: -0.1700

Data Index: 2608588 (Open Web Text)

Max Activating Token Index: 521