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

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

Neuron 1028 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: 0.8208. Min Range: -0.8208

Max Act: 0.8208. Min Act: -0.0001

Data Index: 1231138 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.7770. Min Act: -0.0001

Data Index: 1004907 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1279785 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.6860. Min Act: -0.0001

Data Index: 699369 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.6453. Min Act: -0.0001

Data Index: 928629 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.6854. Min Act: -0.0001

Data Index: 77002 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.6523. Min Act: -0.0001

Data Index: 670457 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.6953. Min Act: -0.0000

Data Index: 639443 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.6434. Min Act: -0.0001

Data Index: 1209860 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.6245. Min Act: -0.0001

Data Index: 743207 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.6817. Min Act: -0.0001

Data Index: 379037 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.6136. Min Act: -0.0001

Data Index: 340545 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.6354. Min Act: -0.0001

Data Index: 727909 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5780. Min Act: -0.0001

Data Index: 636159 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.6106. Min Act: -0.0001

Data Index: 386722 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5885. Min Act: -0.0001

Data Index: 675437 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5844. Min Act: -0.0001

Data Index: 743103 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5863. Min Act: -0.0001

Data Index: 211223 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.5661. Min Act: -0.0001

Data Index: 1195393 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.8208. Min Range: -0.8208

Max Act: 0.6001. Min Act: -0.0001

Data Index: 663163 (C4 (Web Text))

Max Activating Token Index: 971