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

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

Neuron 2956 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.4154. Min Act: -0.0000

Data Index: 478489 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.4209. Min Act: -0.0000

Data Index: 938369 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3845. Min Act: -0.0001

Data Index: 208379 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3496. Min Act: -0.0000

Data Index: 150182 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3469. Min Act: -0.0000

Data Index: 638372 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3524. Min Act: -0.0000

Data Index: 986756 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3499. Min Act: -0.0000

Data Index: 1145680 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3341. Min Act: -0.0000

Data Index: 777382 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1256501 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1149591 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3424. Min Act: -0.0000

Data Index: 121582 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3550. Min Act: -0.0000

Data Index: 69859 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3375. Min Act: -0.0000

Data Index: 394059 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3486. Min Act: -0.0000

Data Index: 292621 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3207. Min Act: -0.0000

Data Index: 766066 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3301. Min Act: -0.0000

Data Index: 160031 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3142. Min Act: -0.0000

Data Index: 625735 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3266. Min Act: -0.0000

Data Index: 220957 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3192. Min Act: -0.0000

Data Index: 911770 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3166. Min Act: -0.0000

Data Index: 356605 (C4 (Web Text))

Max Activating Token Index: 182