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

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

Neuron 1058 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: 0.6205. Min Range: -0.6205

Max Act: 0.6164. Min Act: -0.0001

Data Index: 1083667 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.6205. Min Act: -0.0001

Data Index: 641138 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.6141. Min Act: -0.0001

Data Index: 455144 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5713. Min Act: -0.0001

Data Index: 551233 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5678. Min Act: -0.0001

Data Index: 74214 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5682. Min Act: -0.0001

Data Index: 601327 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5669. Min Act: -0.0001

Data Index: 271751 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5563. Min Act: -0.0001

Data Index: 1312257 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5350. Min Act: -0.0001

Data Index: 1184438 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5498. Min Act: -0.0001

Data Index: 1171921 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5682. Min Act: -0.0001

Data Index: 243706 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5366. Min Act: -0.0001

Data Index: 1326485 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5349. Min Act: -0.0001

Data Index: 754340 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5123. Min Act: -0.0001

Data Index: 978619 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5313. Min Act: -0.0001

Data Index: 265511 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5459. Min Act: -0.0001

Data Index: 1300234 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5208. Min Act: -0.0001

Data Index: 16742 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5027. Min Act: -0.0001

Data Index: 1029384 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5024. Min Act: -0.0001

Data Index: 443016 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 0.6205. Min Range: -0.6205

Max Act: 0.5373. Min Act: -0.0001

Data Index: 961710 (C4 (Web Text))

Max Activating Token Index: 909