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

Dataset: Open Web Text

Neuron 76 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: 4.4851. Min Range: -4.4851

Max Act: 4.4851. Min Act: -0.1700

Data Index: 4999984 (Open Web Text)

Max Activating Token Index: 730

Text #1

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.4492. Min Act: -0.1700

Data Index: 7397306 (Open Web Text)

Max Activating Token Index: 283

Text #2

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.4159. Min Act: -0.1700

Data Index: 4058555 (Open Web Text)

Max Activating Token Index: 151

Text #3

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.3075. Min Act: -0.1700

Data Index: 8630584 (Open Web Text)

Max Activating Token Index: 368

Text #4

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.3391. Min Act: -0.1700

Data Index: 2839397 (Open Web Text)

Max Activating Token Index: 775

Text #5

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.3255. Min Act: -0.1700

Data Index: 6663467 (Open Web Text)

Max Activating Token Index: 218

Text #6

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.2681. Min Act: -0.1700

Data Index: 1287903 (Open Web Text)

Max Activating Token Index: 689

Text #7

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.2856. Min Act: -0.1700

Data Index: 1000338 (Open Web Text)

Max Activating Token Index: 301

Text #8

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.2555. Min Act: -0.1700

Data Index: 8567162 (Open Web Text)

Max Activating Token Index: 251

Text #9

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.2585. Min Act: -0.1700

Data Index: 6909689 (Open Web Text)

Max Activating Token Index: 661

Text #10

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.2273. Min Act: -0.1700

Data Index: 4356198 (Open Web Text)

Max Activating Token Index: 460

Text #11

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.2730. Min Act: -0.1700

Data Index: 1957268 (Open Web Text)

Max Activating Token Index: 623

Text #12

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.2245. Min Act: -0.1700

Data Index: 6779737 (Open Web Text)

Max Activating Token Index: 454

Text #13

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.2301. Min Act: -0.1700

Data Index: 2024587 (Open Web Text)

Max Activating Token Index: 66

Text #14

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.2194. Min Act: -0.1700

Data Index: 1949633 (Open Web Text)

Max Activating Token Index: 962

Text #15

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.2115. Min Act: -0.1700

Data Index: 212590 (Open Web Text)

Max Activating Token Index: 683

Text #16

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.1890. Min Act: -0.1700

Data Index: 4202939 (Open Web Text)

Max Activating Token Index: 284

Text #17

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.2041. Min Act: -0.1700

Data Index: 5408189 (Open Web Text)

Max Activating Token Index: 833

Text #18

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.1599. Min Act: -0.1700

Data Index: 801528 (Open Web Text)

Max Activating Token Index: 772

Text #19

Max Range: 4.4851. Min Range: -4.4851

Max Act: 4.1958. Min Act: -0.1700

Data Index: 3611639 (Open Web Text)

Max Activating Token Index: 907