Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4871 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0868. Min Range: -1.0868

Max Act: 1.0868. Min Act: -0.0000

Data Index: 298238 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.9212. Min Act: -0.0000

Data Index: 231647 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.9310. Min Act: -0.0000

Data Index: 278858 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8447. Min Act: -0.0000

Data Index: 810233 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.7805. Min Act: -0.0000

Data Index: 239995 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.7792. Min Act: -0.0000

Data Index: 741169 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.7816. Min Act: -0.0000

Data Index: 855326 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1296719 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1295721 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1352512 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1274980 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.7182. Min Act: -0.0000

Data Index: 699480 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.7645. Min Act: -0.0000

Data Index: 584990 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.6513. Min Act: -0.0000

Data Index: 646592 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.6457. Min Act: -0.0000

Data Index: 128296 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.6726. Min Act: -0.0000

Data Index: 700194 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.6495. Min Act: -0.0000

Data Index: 729770 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.6408. Min Act: -0.0000

Data Index: 166875 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1211585 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 1.0868. Min Range: -1.0868

Max Act: 0.6224. Min Act: -0.0000

Data Index: 475658 (C4 (Web Text))

Max Activating Token Index: 282