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

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

Neuron 819 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.9814. Min Act: -0.0000

Data Index: 1300371 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.7235. Min Act: -0.0000

Data Index: 471710 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.6237. Min Act: -0.0000

Data Index: 788955 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.4155. Min Act: -0.0000

Data Index: 1070697 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.4250. Min Act: 0.0000

Data Index: 863505 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.3715. Min Act: -0.0000

Data Index: 399211 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.3478. Min Act: -0.0000

Data Index: 1311746 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.3301. Min Act: -0.0000

Data Index: 666105 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.2998. Min Act: -0.0000

Data Index: 259371 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.2930. Min Act: -0.0000

Data Index: 571179 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.2522. Min Act: -0.0000

Data Index: 311284 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1257633 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.1857. Min Act: -0.0000

Data Index: 368154 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.1892. Min Act: -0.0000

Data Index: 469352 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.2129. Min Act: -0.0000

Data Index: 1304526 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.1646. Min Act: -0.0000

Data Index: 1120969 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.1467. Min Act: -0.0000

Data Index: 774569 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.1270. Min Act: -0.0000

Data Index: 806294 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.1485. Min Act: -0.0000

Data Index: 1132520 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 1.9814. Min Range: -1.9814

Max Act: 1.1224. Min Act: -0.0000

Data Index: 740888 (C4 (Web Text))

Max Activating Token Index: 348