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

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

Neuron 926 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1518. Min Act: -0.0001

Data Index: 591270 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1364. Min Act: -0.0001

Data Index: 1160720 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1335. Min Act: -0.0001

Data Index: 13467 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1352. Min Act: -0.0001

Data Index: 936629 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1212. Min Act: -0.0001

Data Index: 1520586 (Python Code)

Max Activating Token Index: 148

Text #5

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1201. Min Act: -0.0001

Data Index: 103329 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1166. Min Act: -0.0001

Data Index: 372487 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1232. Min Act: -0.0001

Data Index: 412860 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1114. Min Act: -0.0001

Data Index: 906439 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1182. Min Act: -0.0001

Data Index: 986702 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1173. Min Act: -0.0001

Data Index: 309598 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1096. Min Act: -0.0001

Data Index: 602646 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1045. Min Act: -0.0001

Data Index: 493912 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1569710 (Python Code)

Max Activating Token Index: 164

Text #14

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1083119 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.0997. Min Act: -0.0001

Data Index: 353706 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1073. Min Act: -0.0001

Data Index: 534855 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1060. Min Act: -0.0001

Data Index: 528965 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1024. Min Act: -0.0001

Data Index: 717544 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.1518. Min Range: -0.1518

Max Act: 0.1132. Min Act: -0.0001

Data Index: 1158737 (C4 (Web Text))

Max Activating Token Index: 24