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

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

Neuron 127 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: 0.3170. Min Range: -0.3170

Max Act: 0.3170. Min Act: -0.0000

Data Index: 1389569 (Python Code)

Max Activating Token Index: 570

Text #1

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2915. Min Act: -0.0000

Data Index: 1170046 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2428. Min Act: -0.0000

Data Index: 376774 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1209034 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1428758 (Python Code)

Max Activating Token Index: 234

Text #5

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2433. Min Act: -0.0000

Data Index: 251171 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2216. Min Act: -0.0000

Data Index: 954373 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2115. Min Act: -0.0000

Data Index: 369720 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1628244 (Python Code)

Max Activating Token Index: 554

Text #9

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2192. Min Act: -0.0000

Data Index: 1652536 (Python Code)

Max Activating Token Index: 587

Text #10

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2028. Min Act: -0.0000

Data Index: 383133 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2062. Min Act: -0.0000

Data Index: 22791 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2084. Min Act: -0.0000

Data Index: 122218 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1429679 (Python Code)

Max Activating Token Index: 398

Text #14

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1974. Min Act: -0.0000

Data Index: 443771 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1492131 (Python Code)

Max Activating Token Index: 765

Text #16

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2014. Min Act: -0.0000

Data Index: 973417 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2133. Min Act: -0.0000

Data Index: 354074 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1221736 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2028. Min Act: -0.0000

Data Index: 1284090 (C4 (Web Text))

Max Activating Token Index: 528