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

Dataset: Open Web Text

Neuron 1558 in Layer 5

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: 5.7486. Min Range: -5.7486

Max Act: 5.6912. Min Act: -0.1700

Data Index: 7176291 (Open Web Text)

Max Activating Token Index: 55

Text #1

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.7123. Min Act: -0.1700

Data Index: 4092348 (Open Web Text)

Max Activating Token Index: 759

Text #2

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.7486. Min Act: -0.1700

Data Index: 1817559 (Open Web Text)

Max Activating Token Index: 201

Text #3

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.6817. Min Act: -0.1700

Data Index: 7636224 (Open Web Text)

Max Activating Token Index: 190

Text #4

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.5352. Min Act: -0.1700

Data Index: 4350762 (Open Web Text)

Max Activating Token Index: 487

Text #5

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.5836. Min Act: -0.1700

Data Index: 2986611 (Open Web Text)

Max Activating Token Index: 755

Text #6

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.5318. Min Act: -0.1700

Data Index: 3523976 (Open Web Text)

Max Activating Token Index: 940

Text #7

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.5461. Min Act: -0.1700

Data Index: 7174080 (Open Web Text)

Max Activating Token Index: 932

Text #8

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.5171. Min Act: -0.1700

Data Index: 195363 (Open Web Text)

Max Activating Token Index: 366

Text #9

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.5244. Min Act: -0.1700

Data Index: 6354271 (Open Web Text)

Max Activating Token Index: 615

Text #10

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.5289. Min Act: -0.1700

Data Index: 3653511 (Open Web Text)

Max Activating Token Index: 744

Text #11

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.5272. Min Act: -0.1700

Data Index: 5168407 (Open Web Text)

Max Activating Token Index: 815

Text #12

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.4742. Min Act: -0.1700

Data Index: 599712 (Open Web Text)

Max Activating Token Index: 756

Text #13

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.5407. Min Act: -0.1700

Data Index: 4753419 (Open Web Text)

Max Activating Token Index: 795

Text #14

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.4589. Min Act: -0.1700

Data Index: 4512104 (Open Web Text)

Max Activating Token Index: 747

Text #15

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.4635. Min Act: -0.1700

Data Index: 234669 (Open Web Text)

Max Activating Token Index: 517

Text #16

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.4650. Min Act: -0.1700

Data Index: 7881824 (Open Web Text)

Max Activating Token Index: 660

Text #17

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.4485. Min Act: -0.1700

Data Index: 2277453 (Open Web Text)

Max Activating Token Index: 504

Text #18

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.4649. Min Act: -0.1700

Data Index: 5546676 (Open Web Text)

Max Activating Token Index: 133

Text #19

Max Range: 5.7486. Min Range: -5.7486

Max Act: 5.4650. Min Act: -0.1700

Data Index: 5447965 (Open Web Text)

Max Activating Token Index: 461