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

Dataset: Open Web Text

Neuron 1587 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: 3.3272. Min Range: -3.3272

Max Act: 3.3272. Min Act: -0.1700

Data Index: 8753723 (Open Web Text)

Max Activating Token Index: 46

Text #1

Max Range: 3.3272. Min Range: -3.3272

Max Act: 3.2911. Min Act: -0.1700

Data Index: 1629661 (Open Web Text)

Max Activating Token Index: 588

Text #2

Max Range: 3.3272. Min Range: -3.3272

Max Act: 3.2589. Min Act: -0.1700

Data Index: 3907558 (Open Web Text)

Max Activating Token Index: 157

Text #3

Max Range: 3.3272. Min Range: -3.3272

Max Act: 3.1153. Min Act: -0.1700

Data Index: 87341 (Open Web Text)

Max Activating Token Index: 337

Text #4

Max Range: 3.3272. Min Range: -3.3272

Max Act: 3.0538. Min Act: -0.1700

Data Index: 3720045 (Open Web Text)

Max Activating Token Index: 106

Text #5

Max Range: 3.3272. Min Range: -3.3272

Max Act: 3.0131. Min Act: -0.1700

Data Index: 7965723 (Open Web Text)

Max Activating Token Index: 109

Text #6

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9825. Min Act: -0.1700

Data Index: 6612013 (Open Web Text)

Max Activating Token Index: 160

Text #7

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9710. Min Act: -0.1700

Data Index: 135943 (Open Web Text)

Max Activating Token Index: 396

Text #8

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9865. Min Act: -0.1700

Data Index: 7621214 (Open Web Text)

Max Activating Token Index: 310

Text #9

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9718. Min Act: -0.1700

Data Index: 5590723 (Open Web Text)

Max Activating Token Index: 215

Text #10

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9873. Min Act: -0.1700

Data Index: 2524068 (Open Web Text)

Max Activating Token Index: 356

Text #11

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9754. Min Act: -0.1700

Data Index: 3001986 (Open Web Text)

Max Activating Token Index: 621

Text #12

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9187. Min Act: -0.1700

Data Index: 5693822 (Open Web Text)

Max Activating Token Index: 431

Text #13

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9414. Min Act: -0.1700

Data Index: 6721266 (Open Web Text)

Max Activating Token Index: 612

Text #14

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9521. Min Act: -0.1700

Data Index: 6889503 (Open Web Text)

Max Activating Token Index: 21

Text #15

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9470. Min Act: -0.1700

Data Index: 2268282 (Open Web Text)

Max Activating Token Index: 351

Text #16

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9530. Min Act: -0.1700

Data Index: 4902752 (Open Web Text)

Max Activating Token Index: 122

Text #17

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9740. Min Act: -0.1700

Data Index: 7391477 (Open Web Text)

Max Activating Token Index: 1021

Text #18

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9407. Min Act: -0.1700

Data Index: 7026799 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9197. Min Act: -0.1700

Data Index: 4169328 (Open Web Text)

Max Activating Token Index: 435