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

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

Neuron 3774 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.3329. Min Act: -0.0002

Data Index: 124969 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.3274. Min Act: -0.0002

Data Index: 1340375 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.3050. Min Act: -0.0002

Data Index: 1275589 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.3027. Min Act: -0.0002

Data Index: 387048 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.3385. Min Act: -0.0002

Data Index: 428597 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2807. Min Act: -0.0002

Data Index: 993672 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2996. Min Act: -0.0002

Data Index: 1201075 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2905. Min Act: -0.0002

Data Index: 1093560 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2736. Min Act: -0.0002

Data Index: 88202 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2510. Min Act: -0.0002

Data Index: 276755 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2912. Min Act: -0.0002

Data Index: 160191 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2527. Min Act: -0.0002

Data Index: 1313595 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.3042. Min Act: -0.0002

Data Index: 502823 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2671. Min Act: -0.0002

Data Index: 908546 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2575. Min Act: -0.0002

Data Index: 818913 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2434. Min Act: -0.0002

Data Index: 930502 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2825. Min Act: -0.0002

Data Index: 839655 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2299. Min Act: -0.0002

Data Index: 338860 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2581. Min Act: -0.0002

Data Index: 39677 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2456. Min Act: -0.0002

Data Index: 475223 (C4 (Web Text))

Max Activating Token Index: 177