Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2204 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.3005. Min Act: -0.0000

Data Index: 496995 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2598. Min Act: -0.0000

Data Index: 934314 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2845. Min Act: -0.0000

Data Index: 217081 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2622. Min Act: -0.0000

Data Index: 949994 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2577. Min Act: -0.0000

Data Index: 468568 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2474. Min Act: -0.0000

Data Index: 833811 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1262324 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2476. Min Act: -0.0000

Data Index: 951475 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2411. Min Act: -0.0000

Data Index: 726823 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2258. Min Act: -0.0000

Data Index: 229946 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2249. Min Act: -0.0000

Data Index: 563672 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2301. Min Act: -0.0000

Data Index: 712613 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2342. Min Act: -0.0000

Data Index: 498386 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1160557 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2194. Min Act: -0.0000

Data Index: 1114459 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2177. Min Act: -0.0000

Data Index: 293480 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2141. Min Act: -0.0000

Data Index: 713655 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2114. Min Act: -0.0000

Data Index: 449799 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1217557 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.3005. Min Range: -0.3005

Max Act: 0.2239. Min Act: -0.0000

Data Index: 253311 (C4 (Web Text))

Max Activating Token Index: 219