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

Dataset: Open Web Text

Neuron 325 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: 3.0289. Min Range: -3.0289

Max Act: 3.0289. Min Act: -0.1700

Data Index: 1695062 (Open Web Text)

Max Activating Token Index: 429

Text #1

Max Range: 3.0289. Min Range: -3.0289

Max Act: 3.0248. Min Act: -0.1700

Data Index: 7181747 (Open Web Text)

Max Activating Token Index: 71

Text #2

Max Range: 3.0289. Min Range: -3.0289

Max Act: 3.0234. Min Act: -0.1700

Data Index: 6351971 (Open Web Text)

Max Activating Token Index: 788

Text #3

Max Range: 3.0289. Min Range: -3.0289

Max Act: 3.0045. Min Act: -0.1700

Data Index: 6672723 (Open Web Text)

Max Activating Token Index: 73

Text #4

Max Range: 3.0289. Min Range: -3.0289

Max Act: 2.9874. Min Act: -0.1700

Data Index: 4055346 (Open Web Text)

Max Activating Token Index: 103

Text #5

Max Range: 3.0289. Min Range: -3.0289

Max Act: 2.9865. Min Act: -0.1700

Data Index: 7985265 (Open Web Text)

Max Activating Token Index: 946

Text #6

Max Range: 3.0289. Min Range: -3.0289

Max Act: 2.9652. Min Act: -0.1700

Data Index: 8073035 (Open Web Text)

Max Activating Token Index: 484

Text #7

Max Range: 3.0289. Min Range: -3.0289

Max Act: 2.9616. Min Act: -0.1700

Data Index: 4009167 (Open Web Text)

Max Activating Token Index: 541

Text #8

Max Range: 3.0289. Min Range: -3.0289

Max Act: 2.9627. Min Act: -0.1700

Data Index: 2510034 (Open Web Text)

Max Activating Token Index: 351

Text #9

Max Range: 3.0289. Min Range: -3.0289

Max Act: 2.9654. Min Act: -0.1700

Data Index: 7884422 (Open Web Text)

Max Activating Token Index: 798

Text #10

Max Range: 3.0289. Min Range: -3.0289

Max Act: 2.9728. Min Act: -0.1700

Data Index: 7649107 (Open Web Text)

Max Activating Token Index: 463

Text #11

Max Range: 3.0289. Min Range: -3.0289

Max Act: 2.9641. Min Act: -0.1700

Data Index: 939410 (Open Web Text)

Max Activating Token Index: 789

Text #12

Max Range: 3.0289. Min Range: -3.0289

Max Act: 2.9485. Min Act: -0.1700

Data Index: 8177194 (Open Web Text)

Max Activating Token Index: 451

Text #13

Max Range: 3.0289. Min Range: -3.0289

Max Act: 2.9459. Min Act: -0.1700

Data Index: 5216229 (Open Web Text)

Max Activating Token Index: 183

Text #14

Max Range: 3.0289. Min Range: -3.0289

Max Act: 2.9508. Min Act: -0.1700

Data Index: 2556697 (Open Web Text)

Max Activating Token Index: 413

Text #15

Max Range: 3.0289. Min Range: -3.0289

Max Act: 2.9549. Min Act: -0.1700

Data Index: 5401013 (Open Web Text)

Max Activating Token Index: 170

Text #16

Max Range: 3.0289. Min Range: -3.0289

Max Act: 2.9440. Min Act: -0.1700

Data Index: 908783 (Open Web Text)

Max Activating Token Index: 772

Text #17

Max Range: 3.0289. Min Range: -3.0289

Max Act: 2.9521. Min Act: -0.1700

Data Index: 8784802 (Open Web Text)

Max Activating Token Index: 736

Text #18

Max Range: 3.0289. Min Range: -3.0289

Max Act: 2.9224. Min Act: -0.1700

Data Index: 6408712 (Open Web Text)

Max Activating Token Index: 762

Text #19

Max Range: 3.0289. Min Range: -3.0289

Max Act: 2.9382. Min Act: -0.1700

Data Index: 6603364 (Open Web Text)

Max Activating Token Index: 697