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

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

Neuron 3655 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3642. Min Range: -1.3642

Max Act: 1.3642. Min Act: -0.0001

Data Index: 944300 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 1.3642. Min Range: -1.3642

Max Act: 1.2051. Min Act: -0.0001

Data Index: 1168215 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 1.3642. Min Range: -1.3642

Max Act: 1.2300. Min Act: -0.0001

Data Index: 841577 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 1.3642. Min Range: -1.3642

Max Act: 1.1557. Min Act: -0.0001

Data Index: 1155309 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 1.3642. Min Range: -1.3642

Max Act: 1.2127. Min Act: -0.0001

Data Index: 290529 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 1.3642. Min Range: -1.3642

Max Act: 1.1078. Min Act: -0.0001

Data Index: 210343 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9906. Min Act: -0.0001

Data Index: 316206 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 1.3642. Min Range: -1.3642

Max Act: 1.0373. Min Act: -0.0001

Data Index: 57414 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 1.3642. Min Range: -1.3642

Max Act: 1.0154. Min Act: -0.0001

Data Index: 978360 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 1.3642. Min Range: -1.3642

Max Act: 1.0221. Min Act: -0.0001

Data Index: 472311 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 1.3642. Min Range: -1.3642

Max Act: 1.0186. Min Act: -0.0001

Data Index: 1223424 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9957. Min Act: -0.0001

Data Index: 667758 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 1.3642. Min Range: -1.3642

Max Act: 1.0230. Min Act: -0.0001

Data Index: 275815 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9980. Min Act: -0.0001

Data Index: 952331 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9164. Min Act: -0.0001

Data Index: 243142 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.9414. Min Act: -0.0001

Data Index: 1227159 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.8291. Min Act: -0.0001

Data Index: 234570 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.8065. Min Act: -0.0001

Data Index: 727618 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.8035. Min Act: -0.0001

Data Index: 1103985 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 1.3642. Min Range: -1.3642

Max Act: 0.8972. Min Act: -0.0001

Data Index: 1226508 (C4 (Web Text))

Max Activating Token Index: 87