Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1738 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0037. Min Act: -0.0006

Data Index: 821250 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0006

Data Index: 410998 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0032. Min Act: -0.0006

Data Index: 196715 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0031. Min Act: -0.0006

Data Index: 378825 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0030. Min Act: -0.0006

Data Index: 1069336 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0031. Min Act: -0.0006

Data Index: 376427 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0031. Min Act: -0.0006

Data Index: 730821 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0030. Min Act: -0.0006

Data Index: 1211648 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0031. Min Act: -0.0006

Data Index: 1236390 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0030. Min Act: -0.0006

Data Index: 392192 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0030. Min Act: -0.0006

Data Index: 236043 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0029. Min Act: -0.0006

Data Index: 265656 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0030. Min Act: -0.0006

Data Index: 494242 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0030. Min Act: -0.0006

Data Index: 58471 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0029. Min Act: -0.0006

Data Index: 575877 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0029. Min Act: -0.0006

Data Index: 1217980 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0029. Min Act: -0.0006

Data Index: 1273795 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0029. Min Act: -0.0006

Data Index: 104302 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0028. Min Act: -0.0006

Data Index: 921287 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0028. Min Act: -0.0006

Data Index: 1326980 (C4 (Web Text))

Max Activating Token Index: 38