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

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

Neuron 3235 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.4398. Min Act: -0.0000

Data Index: 490094 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.2360. Min Act: -0.0000

Data Index: 1055637 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.1663. Min Act: -0.0000

Data Index: 1066241 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.1397. Min Act: -0.0000

Data Index: 678390 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.1224. Min Act: -0.0000

Data Index: 874096 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.0740. Min Act: -0.0000

Data Index: 756898 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 1.4398. Min Range: -1.4398

Max Act: 0.9743. Min Act: -0.0000

Data Index: 363601 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.0166. Min Act: -0.0000

Data Index: 133646 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.0177. Min Act: -0.0000

Data Index: 835815 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.0660. Min Act: -0.0000

Data Index: 167975 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.0004. Min Act: -0.0000

Data Index: 761113 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 1.4398. Min Range: -1.4398

Max Act: 0.9974. Min Act: -0.0000

Data Index: 214318 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 1.4398. Min Range: -1.4398

Max Act: 0.9945. Min Act: -0.0000

Data Index: 966678 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 1.4398. Min Range: -1.4398

Max Act: 1.0279. Min Act: -0.0000

Data Index: 1007141 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 1.4398. Min Range: -1.4398

Max Act: 0.9664. Min Act: -0.0000

Data Index: 259102 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 1.4398. Min Range: -1.4398

Max Act: 0.8992. Min Act: -0.0000

Data Index: 844062 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 1.4398. Min Range: -1.4398

Max Act: 0.8889. Min Act: -0.0000

Data Index: 465851 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 1.4398. Min Range: -1.4398

Max Act: 0.9453. Min Act: -0.0000

Data Index: 1210658 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 1.4398. Min Range: -1.4398

Max Act: 0.8835. Min Act: -0.0000

Data Index: 375957 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 1.4398. Min Range: -1.4398

Max Act: 0.9163. Min Act: -0.0000

Data Index: 459278 (C4 (Web Text))

Max Activating Token Index: 565