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

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

Neuron 905 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1186. Min Act: -0.0001

Data Index: 480693 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1218585 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1249656 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0947. Min Act: -0.0000

Data Index: 572821 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0940. Min Act: -0.0001

Data Index: 858419 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0923. Min Act: -0.0001

Data Index: 214029 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1010600 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0887. Min Act: -0.0000

Data Index: 257523 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0872. Min Act: -0.0001

Data Index: 429787 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0897. Min Act: -0.0001

Data Index: 734024 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0867. Min Act: -0.0000

Data Index: 331128 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0831. Min Act: -0.0000

Data Index: 1162890 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0839. Min Act: -0.0000

Data Index: 1153571 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0838. Min Act: -0.0001

Data Index: 40657 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0833. Min Act: -0.0001

Data Index: 164795 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0833. Min Act: -0.0001

Data Index: 1134161 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0794. Min Act: -0.0000

Data Index: 332053 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0821. Min Act: -0.0000

Data Index: 454905 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0793. Min Act: -0.0001

Data Index: 199497 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0838. Min Act: -0.0001

Data Index: 155684 (C4 (Web Text))

Max Activating Token Index: 205