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

Dataset: Open Web Text

Neuron 846 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: 3.4578. Min Range: -3.4578

Max Act: 3.4578. Min Act: -0.1700

Data Index: 109150 (Open Web Text)

Max Activating Token Index: 930

Text #1

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.4544. Min Act: -0.1700

Data Index: 7678699 (Open Web Text)

Max Activating Token Index: 243

Text #2

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.4217. Min Act: -0.1700

Data Index: 2522259 (Open Web Text)

Max Activating Token Index: 235

Text #3

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.4056. Min Act: -0.1700

Data Index: 4805016 (Open Web Text)

Max Activating Token Index: 743

Text #4

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.4177. Min Act: -0.1700

Data Index: 7863483 (Open Web Text)

Max Activating Token Index: 972

Text #5

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.3946. Min Act: -0.1700

Data Index: 6488453 (Open Web Text)

Max Activating Token Index: 359

Text #6

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.3830. Min Act: -0.1700

Data Index: 7816694 (Open Web Text)

Max Activating Token Index: 642

Text #7

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.3686. Min Act: -0.1700

Data Index: 4833883 (Open Web Text)

Max Activating Token Index: 602

Text #8

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.3210. Min Act: -0.1700

Data Index: 5265154 (Open Web Text)

Max Activating Token Index: 749

Text #9

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.3337. Min Act: -0.1700

Data Index: 4803147 (Open Web Text)

Max Activating Token Index: 822

Text #10

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.3390. Min Act: -0.1700

Data Index: 2220440 (Open Web Text)

Max Activating Token Index: 370

Text #11

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.3236. Min Act: -0.1700

Data Index: 7280170 (Open Web Text)

Max Activating Token Index: 972

Text #12

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.3253. Min Act: -0.1700

Data Index: 8512586 (Open Web Text)

Max Activating Token Index: 130

Text #13

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.3044. Min Act: -0.1700

Data Index: 4112615 (Open Web Text)

Max Activating Token Index: 417

Text #14

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.3245. Min Act: -0.1700

Data Index: 2883933 (Open Web Text)

Max Activating Token Index: 236

Text #15

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.3219. Min Act: -0.1700

Data Index: 4283561 (Open Web Text)

Max Activating Token Index: 133

Text #16

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.3211. Min Act: -0.1700

Data Index: 5170352 (Open Web Text)

Max Activating Token Index: 371

Text #17

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.3006. Min Act: -0.1700

Data Index: 5109392 (Open Web Text)

Max Activating Token Index: 191

Text #18

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.3299. Min Act: -0.1700

Data Index: 1198713 (Open Web Text)

Max Activating Token Index: 205

Text #19

Max Range: 3.4578. Min Range: -3.4578

Max Act: 3.2922. Min Act: -0.1700

Data Index: 2336094 (Open Web Text)

Max Activating Token Index: 831