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

Dataset: Open Web Text

Neuron 505 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: 4.4486. Min Range: -4.4486

Max Act: 4.4486. Min Act: -0.1700

Data Index: 3340090 (Open Web Text)

Max Activating Token Index: 155

Text #1

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.4207. Min Act: -0.1700

Data Index: 6913819 (Open Web Text)

Max Activating Token Index: 826

Text #2

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.4257. Min Act: -0.1700

Data Index: 4042372 (Open Web Text)

Max Activating Token Index: 345

Text #3

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.4068. Min Act: -0.1700

Data Index: 8608913 (Open Web Text)

Max Activating Token Index: 740

Text #4

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.3555. Min Act: -0.1700

Data Index: 8766866 (Open Web Text)

Max Activating Token Index: 748

Text #5

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.3860. Min Act: -0.1700

Data Index: 4375269 (Open Web Text)

Max Activating Token Index: 343

Text #6

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.3508. Min Act: -0.1700

Data Index: 462050 (Open Web Text)

Max Activating Token Index: 495

Text #7

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.3217. Min Act: -0.1700

Data Index: 5690353 (Open Web Text)

Max Activating Token Index: 170

Text #8

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.3611. Min Act: -0.1700

Data Index: 5861140 (Open Web Text)

Max Activating Token Index: 86

Text #9

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.3244. Min Act: -0.1700

Data Index: 2780063 (Open Web Text)

Max Activating Token Index: 204

Text #10

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.3294. Min Act: -0.1700

Data Index: 7477617 (Open Web Text)

Max Activating Token Index: 216

Text #11

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.3383. Min Act: -0.1700

Data Index: 8708276 (Open Web Text)

Max Activating Token Index: 565

Text #12

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.3380. Min Act: -0.1700

Data Index: 1378415 (Open Web Text)

Max Activating Token Index: 356

Text #13

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.3284. Min Act: -0.1700

Data Index: 8203632 (Open Web Text)

Max Activating Token Index: 675

Text #14

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.3744. Min Act: -0.1700

Data Index: 5037936 (Open Web Text)

Max Activating Token Index: 663

Text #15

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.2885. Min Act: -0.1700

Data Index: 7011286 (Open Web Text)

Max Activating Token Index: 743

Text #16

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.3039. Min Act: -0.1700

Data Index: 6619352 (Open Web Text)

Max Activating Token Index: 276

Text #17

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.3279. Min Act: -0.1700

Data Index: 3519004 (Open Web Text)

Max Activating Token Index: 164

Text #18

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.3173. Min Act: -0.1700

Data Index: 2774033 (Open Web Text)

Max Activating Token Index: 253

Text #19

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.3403. Min Act: -0.1700

Data Index: 1967442 (Open Web Text)

Max Activating Token Index: 314