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

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

Neuron 924 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.7193. Min Act: -0.0000

Data Index: 944781 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6951. Min Act: -0.0000

Data Index: 791460 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6855. Min Act: -0.0001

Data Index: 96377 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1003628 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6746. Min Act: -0.0001

Data Index: 923092 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6193. Min Act: -0.0000

Data Index: 105122 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6257. Min Act: -0.0000

Data Index: 119861 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6261. Min Act: -0.0000

Data Index: 621103 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6401. Min Act: -0.0000

Data Index: 26412 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6336. Min Act: -0.0001

Data Index: 974838 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6390. Min Act: -0.0001

Data Index: 1144201 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6151. Min Act: -0.0001

Data Index: 1198705 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6518. Min Act: -0.0001

Data Index: 860323 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1121347 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6395. Min Act: -0.0001

Data Index: 217281 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5938. Min Act: -0.0001

Data Index: 987431 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5946. Min Act: -0.0000

Data Index: 973979 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.6192. Min Act: -0.0000

Data Index: 1161116 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5519. Min Act: -0.0001

Data Index: 998955 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.7193. Min Range: -0.7193

Max Act: 0.5672. Min Act: -0.0000

Data Index: 74098 (C4 (Web Text))

Max Activating Token Index: 113