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

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

Neuron 3973 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3982. Min Act: -0.0000

Data Index: 102172 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3742. Min Act: -0.0000

Data Index: 1323071 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3731. Min Act: -0.0000

Data Index: 67367 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3527. Min Act: -0.0000

Data Index: 433458 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3574. Min Act: -0.0000

Data Index: 891643 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3628. Min Act: -0.0000

Data Index: 628030 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3474. Min Act: -0.0000

Data Index: 923995 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3199. Min Act: -0.0000

Data Index: 1171136 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2845. Min Act: -0.0000

Data Index: 436896 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3360. Min Act: -0.0000

Data Index: 189792 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1285660 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2997. Min Act: -0.0000

Data Index: 409924 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1333840 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2858. Min Act: -0.0000

Data Index: 1001328 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2841. Min Act: 0.0000

Data Index: 839271 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2793. Min Act: -0.0000

Data Index: 592451 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2837. Min Act: -0.0000

Data Index: 509677 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2805. Min Act: -0.0000

Data Index: 480772 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2730. Min Act: -0.0000

Data Index: 78079 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.2711. Min Act: -0.0000

Data Index: 795857 (C4 (Web Text))

Max Activating Token Index: 401