Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1375 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0037. Min Act: -0.0003

Data Index: 59623 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0036. Min Act: -0.0002

Data Index: 4682 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0002

Data Index: 1616914 (Python Code)

Max Activating Token Index: 288

Text #3

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0035. Min Act: -0.0002

Data Index: 900072 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0003

Data Index: 400293 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0033. Min Act: -0.0002

Data Index: 431633 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0033. Min Act: -0.0003

Data Index: 982244 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0033. Min Act: -0.0003

Data Index: 1519685 (Python Code)

Max Activating Token Index: 171

Text #8

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0033. Min Act: -0.0003

Data Index: 688545 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0031. Min Act: -0.0002

Data Index: 665857 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0033. Min Act: -0.0003

Data Index: 24841 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0032. Min Act: -0.0003

Data Index: 1410358 (Python Code)

Max Activating Token Index: 178

Text #12

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0032. Min Act: -0.0002

Data Index: 589148 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0030. Min Act: -0.0003

Data Index: 1290706 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0030. Min Act: -0.0003

Data Index: 901345 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0030. Min Act: -0.0003

Data Index: 1169275 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0030. Min Act: -0.0003

Data Index: 897379 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0030. Min Act: -0.0003

Data Index: 1410795 (Python Code)

Max Activating Token Index: 295

Text #18

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0028. Min Act: -0.0002

Data Index: 787220 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0030. Min Act: -0.0003

Data Index: 1226001 (C4 (Web Text))

Max Activating Token Index: 74