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

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

Neuron 3487 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: 1.2231. Min Range: -1.2231

Max Act: 1.2231. Min Act: -0.0000

Data Index: 605749 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 1.2231. Min Range: -1.2231

Max Act: 1.1921. Min Act: -0.0000

Data Index: 92978 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 1.2231. Min Range: -1.2231

Max Act: 1.1805. Min Act: -0.0000

Data Index: 1645202 (Python Code)

Max Activating Token Index: 902

Text #3

Max Range: 1.2231. Min Range: -1.2231

Max Act: 0.9578. Min Act: -0.0000

Data Index: 593326 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 1.2231. Min Range: -1.2231

Max Act: 1.0683. Min Act: -0.0000

Data Index: 1605951 (Python Code)

Max Activating Token Index: 933

Text #5

Max Range: 1.2231. Min Range: -1.2231

Max Act: 0.9543. Min Act: -0.0000

Data Index: 1603886 (Python Code)

Max Activating Token Index: 154

Text #6

Max Range: 1.2231. Min Range: -1.2231

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1583096 (Python Code)

Max Activating Token Index: 717

Text #7

Max Range: 1.2231. Min Range: -1.2231

Max Act: 0.9069. Min Act: -0.0000

Data Index: 1461098 (Python Code)

Max Activating Token Index: 158

Text #8

Max Range: 1.2231. Min Range: -1.2231

Max Act: 0.8223. Min Act: -0.0000

Data Index: 190001 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 1.2231. Min Range: -1.2231

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1628780 (Python Code)

Max Activating Token Index: 826

Text #10

Max Range: 1.2231. Min Range: -1.2231

Max Act: 0.9326. Min Act: -0.0000

Data Index: 30625 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 1.2231. Min Range: -1.2231

Max Act: 0.8521. Min Act: -0.0000

Data Index: 1399156 (Python Code)

Max Activating Token Index: 227

Text #12

Max Range: 1.2231. Min Range: -1.2231

Max Act: 0.8367. Min Act: -0.0000

Data Index: 1062420 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 1.2231. Min Range: -1.2231

Max Act: 0.7572. Min Act: -0.0000

Data Index: 1471214 (Python Code)

Max Activating Token Index: 45

Text #14

Max Range: 1.2231. Min Range: -1.2231

Max Act: 0.7517. Min Act: -0.0000

Data Index: 1652085 (Python Code)

Max Activating Token Index: 689

Text #15

Max Range: 1.2231. Min Range: -1.2231

Max Act: 0.7286. Min Act: -0.0000

Data Index: 296968 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 1.2231. Min Range: -1.2231

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1423912 (Python Code)

Max Activating Token Index: 985

Text #17

Max Range: 1.2231. Min Range: -1.2231

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1655665 (Python Code)

Max Activating Token Index: 562

Text #18

Max Range: 1.2231. Min Range: -1.2231

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1460152 (Python Code)

Max Activating Token Index: 87

Text #19

Max Range: 1.2231. Min Range: -1.2231

Max Act: 0.5577. Min Act: -0.0000

Data Index: 796946 (C4 (Web Text))

Max Activating Token Index: 619