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

Dataset: Open Web Text

Neuron 787 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: 3.7551. Min Range: -3.7551

Max Act: 3.7551. Min Act: -0.1700

Data Index: 7639289 (Open Web Text)

Max Activating Token Index: 454

Text #1

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.7063. Min Act: -0.1700

Data Index: 5979231 (Open Web Text)

Max Activating Token Index: 830

Text #2

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.6680. Min Act: -0.1700

Data Index: 2955095 (Open Web Text)

Max Activating Token Index: 706

Text #3

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.6539. Min Act: -0.1700

Data Index: 5127411 (Open Web Text)

Max Activating Token Index: 524

Text #4

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.6088. Min Act: -0.1700

Data Index: 6444494 (Open Web Text)

Max Activating Token Index: 45

Text #5

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.6276. Min Act: -0.1700

Data Index: 5217847 (Open Web Text)

Max Activating Token Index: 711

Text #6

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.5667. Min Act: -0.1700

Data Index: 5633322 (Open Web Text)

Max Activating Token Index: 379

Text #7

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.5478. Min Act: -0.1700

Data Index: 4638289 (Open Web Text)

Max Activating Token Index: 481

Text #8

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.5578. Min Act: -0.1700

Data Index: 125848 (Open Web Text)

Max Activating Token Index: 72

Text #9

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.5588. Min Act: -0.1700

Data Index: 8796161 (Open Web Text)

Max Activating Token Index: 181

Text #10

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.5694. Min Act: -0.1700

Data Index: 4709130 (Open Web Text)

Max Activating Token Index: 567

Text #11

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.5390. Min Act: -0.1700

Data Index: 4099370 (Open Web Text)

Max Activating Token Index: 300

Text #12

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.5524. Min Act: -0.1700

Data Index: 3562174 (Open Web Text)

Max Activating Token Index: 757

Text #13

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.5005. Min Act: -0.1700

Data Index: 2900547 (Open Web Text)

Max Activating Token Index: 91

Text #14

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.5219. Min Act: -0.1700

Data Index: 1580456 (Open Web Text)

Max Activating Token Index: 511

Text #15

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.5244. Min Act: -0.1700

Data Index: 2866914 (Open Web Text)

Max Activating Token Index: 530

Text #16

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.5183. Min Act: -0.1700

Data Index: 574725 (Open Web Text)

Max Activating Token Index: 614

Text #17

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.5128. Min Act: -0.1700

Data Index: 3267849 (Open Web Text)

Max Activating Token Index: 735

Text #18

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.4887. Min Act: -0.1700

Data Index: 3218914 (Open Web Text)

Max Activating Token Index: 162

Text #19

Max Range: 3.7551. Min Range: -3.7551

Max Act: 3.4892. Min Act: -0.1700

Data Index: 1688972 (Open Web Text)

Max Activating Token Index: 304