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

Dataset: Open Web Text

Neuron 2696 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: 3.4205. Min Range: -3.4205

Max Act: 3.4205. Min Act: -0.1700

Data Index: 6275654 (Open Web Text)

Max Activating Token Index: 142

Text #1

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.3721. Min Act: -0.1700

Data Index: 1275679 (Open Web Text)

Max Activating Token Index: 322

Text #2

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.3484. Min Act: -0.1700

Data Index: 4141346 (Open Web Text)

Max Activating Token Index: 662

Text #3

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.3507. Min Act: -0.1700

Data Index: 6776818 (Open Web Text)

Max Activating Token Index: 332

Text #4

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.3321. Min Act: -0.1700

Data Index: 1516607 (Open Web Text)

Max Activating Token Index: 496

Text #5

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.3271. Min Act: -0.1700

Data Index: 5456488 (Open Web Text)

Max Activating Token Index: 295

Text #6

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.3000. Min Act: -0.1700

Data Index: 8261047 (Open Web Text)

Max Activating Token Index: 933

Text #7

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.2999. Min Act: -0.1700

Data Index: 6734959 (Open Web Text)

Max Activating Token Index: 524

Text #8

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.2970. Min Act: -0.1700

Data Index: 8467533 (Open Web Text)

Max Activating Token Index: 437

Text #9

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.2925. Min Act: -0.1700

Data Index: 3804378 (Open Web Text)

Max Activating Token Index: 54

Text #10

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.2697. Min Act: -0.1700

Data Index: 6554691 (Open Web Text)

Max Activating Token Index: 927

Text #11

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.2616. Min Act: -0.1700

Data Index: 6662701 (Open Web Text)

Max Activating Token Index: 376

Text #12

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.2720. Min Act: -0.1700

Data Index: 7717873 (Open Web Text)

Max Activating Token Index: 730

Text #13

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.2586. Min Act: -0.1700

Data Index: 4256533 (Open Web Text)

Max Activating Token Index: 829

Text #14

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.2697. Min Act: -0.1700

Data Index: 6124108 (Open Web Text)

Max Activating Token Index: 708

Text #15

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.2509. Min Act: -0.1700

Data Index: 6757478 (Open Web Text)

Max Activating Token Index: 330

Text #16

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.2484. Min Act: -0.1700

Data Index: 2747823 (Open Web Text)

Max Activating Token Index: 869

Text #17

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.2389. Min Act: -0.1700

Data Index: 6367399 (Open Web Text)

Max Activating Token Index: 507

Text #18

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.2541. Min Act: -0.1700

Data Index: 2401559 (Open Web Text)

Max Activating Token Index: 390

Text #19

Max Range: 3.4205. Min Range: -3.4205

Max Act: 3.2258. Min Act: -0.1700

Data Index: 1618341 (Open Web Text)

Max Activating Token Index: 783