Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5090 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.8230. Min Act: -0.0000

Data Index: 771167 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.8181. Min Act: -0.0000

Data Index: 1272518 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.7981. Min Act: -0.0000

Data Index: 996209 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.6708. Min Act: -0.0000

Data Index: 545909 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1281368 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.6019. Min Act: -0.0000

Data Index: 329474 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.6029. Min Act: -0.0000

Data Index: 689805 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5701. Min Act: -0.0000

Data Index: 748373 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1309371 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.6008. Min Act: -0.0000

Data Index: 287186 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1278434 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5567. Min Act: -0.0000

Data Index: 177216 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5608. Min Act: -0.0000

Data Index: 403003 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1232334 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5477. Min Act: -0.0000

Data Index: 989719 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5582. Min Act: -0.0000

Data Index: 788497 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1162036 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1079769 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.5151. Min Act: -0.0000

Data Index: 464531 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 0.8230. Min Range: -0.8230

Max Act: 0.4781. Min Act: -0.0000

Data Index: 387366 (C4 (Web Text))

Max Activating Token Index: 414