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

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

Neuron 3401 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1357. Min Act: -0.0000

Data Index: 886081 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1244. Min Act: -0.0000

Data Index: 1149638 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1302666 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1053592 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1072. Min Act: 0.0000

Data Index: 1480241 (Python Code)

Max Activating Token Index: 846

Text #5

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1018. Min Act: -0.0000

Data Index: 135834 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1078. Min Act: -0.0000

Data Index: 367212 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1021. Min Act: -0.0000

Data Index: 391707 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1032. Min Act: -0.0000

Data Index: 365100 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0979. Min Act: -0.0000

Data Index: 208161 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1022. Min Act: -0.0000

Data Index: 567247 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1102751 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1046. Min Act: -0.0000

Data Index: 219044 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1017. Min Act: -0.0000

Data Index: 1095253 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1013. Min Act: -0.0000

Data Index: 163230 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1656262 (Python Code)

Max Activating Token Index: 158

Text #16

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1061978 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0939. Min Act: -0.0000

Data Index: 695386 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0952. Min Act: -0.0000

Data Index: 869718 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0909. Min Act: -0.0000

Data Index: 847245 (C4 (Web Text))

Max Activating Token Index: 648