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

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

Neuron 92 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.9926. Min Act: -0.0001

Data Index: 1101064 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.8912. Min Act: -0.0001

Data Index: 430375 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.6762. Min Act: -0.0001

Data Index: 1362668 (Python Code)

Max Activating Token Index: 941

Text #3

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.8642. Min Act: -0.0001

Data Index: 1013884 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.7955. Min Act: -0.0000

Data Index: 76635 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.7743. Min Act: -0.0001

Data Index: 1074098 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.8175. Min Act: -0.0001

Data Index: 1366992 (Python Code)

Max Activating Token Index: 339

Text #7

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.7194. Min Act: -0.0001

Data Index: 1021240 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.8208. Min Act: -0.0001

Data Index: 1163128 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.7345. Min Act: -0.0001

Data Index: 158818 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.6246. Min Act: -0.0001

Data Index: 1405818 (Python Code)

Max Activating Token Index: 398

Text #11

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.6588. Min Act: -0.0001

Data Index: 1111099 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.7417. Min Act: -0.0001

Data Index: 707183 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.6367. Min Act: -0.0001

Data Index: 1576513 (Python Code)

Max Activating Token Index: 832

Text #14

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.5993. Min Act: -0.0001

Data Index: 335599 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.6427. Min Act: -0.0000

Data Index: 417295 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.6798. Min Act: -0.0001

Data Index: 1194951 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.7784. Min Act: -0.0001

Data Index: 1498235 (Python Code)

Max Activating Token Index: 879

Text #18

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.6601. Min Act: -0.0001

Data Index: 1266276 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.5986. Min Act: -0.0001

Data Index: 464732 (C4 (Web Text))

Max Activating Token Index: 554