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

Dataset: Open Web Text

Neuron 2454 in Layer 6

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: 3.9557. Min Range: -3.9557

Max Act: 3.9557. Min Act: -0.1700

Data Index: 1936110 (Open Web Text)

Max Activating Token Index: 969

Text #1

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.8810. Min Act: -0.1700

Data Index: 4638563 (Open Web Text)

Max Activating Token Index: 667

Text #2

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.7941. Min Act: -0.1700

Data Index: 4962798 (Open Web Text)

Max Activating Token Index: 863

Text #3

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.6411. Min Act: -0.1700

Data Index: 7632171 (Open Web Text)

Max Activating Token Index: 951

Text #4

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.5958. Min Act: -0.1700

Data Index: 264943 (Open Web Text)

Max Activating Token Index: 549

Text #5

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.5667. Min Act: -0.1700

Data Index: 2748095 (Open Web Text)

Max Activating Token Index: 505

Text #6

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.5625. Min Act: -0.1700

Data Index: 6958329 (Open Web Text)

Max Activating Token Index: 148

Text #7

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.5369. Min Act: -0.1700

Data Index: 7742319 (Open Web Text)

Max Activating Token Index: 652

Text #8

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.5626. Min Act: -0.1700

Data Index: 7018708 (Open Web Text)

Max Activating Token Index: 1009

Text #9

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.5648. Min Act: -0.1700

Data Index: 851627 (Open Web Text)

Max Activating Token Index: 141

Text #10

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.5383. Min Act: -0.1700

Data Index: 4890972 (Open Web Text)

Max Activating Token Index: 51

Text #11

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.5386. Min Act: -0.1700

Data Index: 6786103 (Open Web Text)

Max Activating Token Index: 1015

Text #12

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.5466. Min Act: -0.1700

Data Index: 616233 (Open Web Text)

Max Activating Token Index: 131

Text #13

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.5202. Min Act: -0.1700

Data Index: 6496570 (Open Web Text)

Max Activating Token Index: 859

Text #14

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.5460. Min Act: -0.1700

Data Index: 4589735 (Open Web Text)

Max Activating Token Index: 990

Text #15

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.5237. Min Act: -0.1700

Data Index: 3718663 (Open Web Text)

Max Activating Token Index: 522

Text #16

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.4852. Min Act: -0.1700

Data Index: 6385555 (Open Web Text)

Max Activating Token Index: 988

Text #17

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.5160. Min Act: -0.1700

Data Index: 6722830 (Open Web Text)

Max Activating Token Index: 460

Text #18

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.4905. Min Act: -0.1700

Data Index: 582102 (Open Web Text)

Max Activating Token Index: 868

Text #19

Max Range: 3.9557. Min Range: -3.9557

Max Act: 3.4908. Min Act: -0.1700

Data Index: 1180276 (Open Web Text)

Max Activating Token Index: 663