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

Dataset: Open Web Text

Neuron 1804 in Layer 1

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: 1.4406. Min Range: -1.4406

Max Act: 1.4369. Min Act: -0.1700

Data Index: 1133154 (Open Web Text)

Max Activating Token Index: 116

Text #1

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.4406. Min Act: -0.1698

Data Index: 3129358 (Open Web Text)

Max Activating Token Index: 251

Text #2

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.4345. Min Act: -0.1700

Data Index: 8247841 (Open Web Text)

Max Activating Token Index: 1019

Text #3

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.4289. Min Act: -0.1689

Data Index: 6219709 (Open Web Text)

Max Activating Token Index: 186

Text #4

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3875. Min Act: -0.1700

Data Index: 3967596 (Open Web Text)

Max Activating Token Index: 857

Text #5

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3823. Min Act: -0.1700

Data Index: 3129357 (Open Web Text)

Max Activating Token Index: 710

Text #6

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3689. Min Act: -0.1700

Data Index: 6450251 (Open Web Text)

Max Activating Token Index: 541

Text #7

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3732. Min Act: -0.1700

Data Index: 5597248 (Open Web Text)

Max Activating Token Index: 209

Text #8

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3565. Min Act: -0.1698

Data Index: 5263890 (Open Web Text)

Max Activating Token Index: 536

Text #9

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3416. Min Act: -0.1700

Data Index: 7349154 (Open Web Text)

Max Activating Token Index: 483

Text #10

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3490. Min Act: -0.1698

Data Index: 3499471 (Open Web Text)

Max Activating Token Index: 332

Text #11

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3419. Min Act: -0.1700

Data Index: 3030726 (Open Web Text)

Max Activating Token Index: 35

Text #12

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3518. Min Act: -0.1700

Data Index: 5848201 (Open Web Text)

Max Activating Token Index: 266

Text #13

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3336. Min Act: -0.1699

Data Index: 8730383 (Open Web Text)

Max Activating Token Index: 204

Text #14

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3310. Min Act: -0.1698

Data Index: 3530962 (Open Web Text)

Max Activating Token Index: 129

Text #15

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3389. Min Act: -0.1699

Data Index: 5597805 (Open Web Text)

Max Activating Token Index: 270

Text #16

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3220. Min Act: -0.1700

Data Index: 578728 (Open Web Text)

Max Activating Token Index: 151

Text #17

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3308. Min Act: -0.1692

Data Index: 5346861 (Open Web Text)

Max Activating Token Index: 179

Text #18

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3338. Min Act: -0.1700

Data Index: 5369853 (Open Web Text)

Max Activating Token Index: 543

Text #19

Max Range: 1.4406. Min Range: -1.4406

Max Act: 1.3341. Min Act: -0.1700

Data Index: 5379258 (Open Web Text)

Max Activating Token Index: 433