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

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

Neuron 941 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: 2.9240. Min Range: -2.9240

Max Act: 2.9240. Min Act: -0.0000

Data Index: 1046852 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 2.9240. Min Range: -2.9240

Max Act: 1.7154. Min Act: -0.0000

Data Index: 1155963 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 2.9240. Min Range: -2.9240

Max Act: 1.1437. Min Act: -0.0000

Data Index: 686453 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 2.9240. Min Range: -2.9240

Max Act: 1.2344. Min Act: -0.0000

Data Index: 124900 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 2.9240. Min Range: -2.9240

Max Act: 1.1202. Min Act: -0.0000

Data Index: 894001 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 2.9240. Min Range: -2.9240

Max Act: 1.1640. Min Act: -0.0000

Data Index: 401468 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 2.9240. Min Range: -2.9240

Max Act: 1.0700. Min Act: -0.0000

Data Index: 1109189 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 2.9240. Min Range: -2.9240

Max Act: 1.1215. Min Act: -0.0000

Data Index: 111376 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 2.9240. Min Range: -2.9240

Max Act: 1.0873. Min Act: -0.0000

Data Index: 335080 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 2.9240. Min Range: -2.9240

Max Act: 1.1412. Min Act: -0.0000

Data Index: 781477 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 2.9240. Min Range: -2.9240

Max Act: 1.1505. Min Act: -0.0000

Data Index: 300157 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 2.9240. Min Range: -2.9240

Max Act: 1.0779. Min Act: -0.0000

Data Index: 1162868 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 2.9240. Min Range: -2.9240

Max Act: 1.1181. Min Act: -0.0000

Data Index: 172329 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 2.9240. Min Range: -2.9240

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1038699 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 2.9240. Min Range: -2.9240

Max Act: 1.0373. Min Act: -0.0000

Data Index: 975661 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 2.9240. Min Range: -2.9240

Max Act: 1.0766. Min Act: -0.0000

Data Index: 137708 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 2.9240. Min Range: -2.9240

Max Act: 1.0430. Min Act: -0.0000

Data Index: 129811 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 2.9240. Min Range: -2.9240

Max Act: 0.9728. Min Act: -0.0000

Data Index: 176195 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 2.9240. Min Range: -2.9240

Max Act: 0.9538. Min Act: -0.0000

Data Index: 1195889 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 2.9240. Min Range: -2.9240

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1181020 (C4 (Web Text))

Max Activating Token Index: 572