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

Dataset: Open Web Text

Neuron 171 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: 4.8979. Min Range: -4.8979

Max Act: 4.8979. Min Act: -0.1700

Data Index: 1018486 (Open Web Text)

Max Activating Token Index: 578

Text #1

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.8728. Min Act: -0.1700

Data Index: 6183507 (Open Web Text)

Max Activating Token Index: 844

Text #2

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.8519. Min Act: -0.1700

Data Index: 2712486 (Open Web Text)

Max Activating Token Index: 509

Text #3

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.8334. Min Act: -0.1700

Data Index: 3886230 (Open Web Text)

Max Activating Token Index: 772

Text #4

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.8160. Min Act: -0.1700

Data Index: 1079212 (Open Web Text)

Max Activating Token Index: 750

Text #5

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.8005. Min Act: -0.1700

Data Index: 8193241 (Open Web Text)

Max Activating Token Index: 315

Text #6

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.8319. Min Act: -0.1700

Data Index: 960215 (Open Web Text)

Max Activating Token Index: 490

Text #7

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.7685. Min Act: -0.1700

Data Index: 5611689 (Open Web Text)

Max Activating Token Index: 357

Text #8

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.7807. Min Act: -0.1700

Data Index: 7559186 (Open Web Text)

Max Activating Token Index: 280

Text #9

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.7869. Min Act: -0.1700

Data Index: 7514165 (Open Web Text)

Max Activating Token Index: 118

Text #10

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.8027. Min Act: -0.1700

Data Index: 7251707 (Open Web Text)

Max Activating Token Index: 191

Text #11

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.7662. Min Act: -0.1700

Data Index: 6387486 (Open Web Text)

Max Activating Token Index: 165

Text #12

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.7709. Min Act: -0.1700

Data Index: 7793526 (Open Web Text)

Max Activating Token Index: 248

Text #13

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.7461. Min Act: -0.1700

Data Index: 5112097 (Open Web Text)

Max Activating Token Index: 1019

Text #14

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.7418. Min Act: -0.1700

Data Index: 8034945 (Open Web Text)

Max Activating Token Index: 733

Text #15

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.7393. Min Act: -0.1700

Data Index: 662083 (Open Web Text)

Max Activating Token Index: 522

Text #16

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.7741. Min Act: -0.1700

Data Index: 5267083 (Open Web Text)

Max Activating Token Index: 73

Text #17

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.7433. Min Act: -0.1700

Data Index: 3453732 (Open Web Text)

Max Activating Token Index: 577

Text #18

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.7336. Min Act: -0.1700

Data Index: 8038653 (Open Web Text)

Max Activating Token Index: 585

Text #19

Max Range: 4.8979. Min Range: -4.8979

Max Act: 4.7463. Min Act: -0.1700

Data Index: 2846947 (Open Web Text)

Max Activating Token Index: 496