Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 715 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0655. Min Act: -0.0001

Data Index: 824197 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0305. Min Act: -0.0001

Data Index: 46379 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0330. Min Act: -0.0001

Data Index: 1123505 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1010562 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0341. Min Act: -0.0001

Data Index: 220314 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0255. Min Act: -0.0001

Data Index: 674166 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0271. Min Act: -0.0001

Data Index: 736768 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0195. Min Act: -0.0001

Data Index: 1174225 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0260. Min Act: -0.0001

Data Index: 516368 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0266. Min Act: -0.0001

Data Index: 1344138 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0258. Min Act: -0.0001

Data Index: 1005693 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0219. Min Act: -0.0001

Data Index: 287862 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0200. Min Act: -0.0001

Data Index: 69296 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0174. Min Act: -0.0001

Data Index: 883730 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0253. Min Act: -0.0001

Data Index: 1201745 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0226. Min Act: -0.0001

Data Index: 174725 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0203. Min Act: -0.0001

Data Index: 944403 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0277. Min Act: -0.0001

Data Index: 819410 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0237. Min Act: -0.0001

Data Index: 102839 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0234. Min Act: -0.0001

Data Index: 343879 (C4 (Web Text))

Max Activating Token Index: 864