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

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

Neuron 1402 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: 1.6532. Min Range: -1.6532

Max Act: 1.6532. Min Act: -0.0000

Data Index: 475912 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 1.6532. Min Range: -1.6532

Max Act: 1.3758. Min Act: -0.0000

Data Index: 763591 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 1.6532. Min Range: -1.6532

Max Act: 1.2272. Min Act: -0.0000

Data Index: 396995 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 1.6532. Min Range: -1.6532

Max Act: 1.0185. Min Act: -0.0000

Data Index: 774654 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 1.6532. Min Range: -1.6532

Max Act: 1.1060. Min Act: -0.0000

Data Index: 332901 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 1.6532. Min Range: -1.6532

Max Act: 1.0298. Min Act: -0.0000

Data Index: 554763 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 1.6532. Min Range: -1.6532

Max Act: 0.9855. Min Act: -0.0000

Data Index: 62995 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 1.6532. Min Range: -1.6532

Max Act: 0.9875. Min Act: -0.0000

Data Index: 497920 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 1.6532. Min Range: -1.6532

Max Act: 0.9050. Min Act: -0.0000

Data Index: 52090 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 1.6532. Min Range: -1.6532

Max Act: 0.9841. Min Act: -0.0000

Data Index: 247317 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 1.6532. Min Range: -1.6532

Max Act: 0.8480. Min Act: -0.0000

Data Index: 319915 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 1.6532. Min Range: -1.6532

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1056001 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 1.6532. Min Range: -1.6532

Max Act: 0.8835. Min Act: -0.0000

Data Index: 444334 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 1.6532. Min Range: -1.6532

Max Act: 0.7995. Min Act: -0.0000

Data Index: 1213089 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 1.6532. Min Range: -1.6532

Max Act: 0.7957. Min Act: -0.0000

Data Index: 1224035 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 1.6532. Min Range: -1.6532

Max Act: 0.7489. Min Act: -0.0000

Data Index: 800782 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 1.6532. Min Range: -1.6532

Max Act: 0.7508. Min Act: -0.0000

Data Index: 468755 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 1.6532. Min Range: -1.6532

Max Act: 0.7568. Min Act: -0.0000

Data Index: 69461 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 1.6532. Min Range: -1.6532

Max Act: 0.7665. Min Act: -0.0000

Data Index: 558655 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 1.6532. Min Range: -1.6532

Max Act: 0.7352. Min Act: -0.0000

Data Index: 232410 (C4 (Web Text))

Max Activating Token Index: 60