Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1873 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.7192. Min Act: -0.0001

Data Index: 790961 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.4252. Min Act: -0.0001

Data Index: 327067 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.5292. Min Act: -0.0001

Data Index: 719529 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.4647. Min Act: -0.0001

Data Index: 806999 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.4159. Min Act: -0.0001

Data Index: 500616 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.4166. Min Act: -0.0001

Data Index: 813901 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.4461. Min Act: -0.0001

Data Index: 1212201 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.3542. Min Act: -0.0001

Data Index: 950228 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.3444. Min Act: -0.0001

Data Index: 1084066 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.3711. Min Act: -0.0001

Data Index: 666503 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.3413. Min Act: -0.0001

Data Index: 1006620 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.2575. Min Act: -0.0001

Data Index: 1308009 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.2323. Min Act: -0.0001

Data Index: 333631 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.2858. Min Act: -0.0001

Data Index: 1136535 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.3024. Min Act: -0.0001

Data Index: 1081915 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.1768. Min Act: -0.0001

Data Index: 263767 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.3079. Min Act: -0.0001

Data Index: 441287 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.2376. Min Act: -0.0001

Data Index: 688836 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.2986. Min Act: -0.0001

Data Index: 391591 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 1.7192. Min Range: -1.7192

Max Act: 1.2619. Min Act: -0.0001

Data Index: 478165 (C4 (Web Text))

Max Activating Token Index: 147