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

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

Neuron 4637 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.8263. Min Act: -0.0001

Data Index: 666045 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7765. Min Act: -0.0001

Data Index: 1136166 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6623. Min Act: -0.0001

Data Index: 260603 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7151. Min Act: -0.0001

Data Index: 604867 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7118. Min Act: -0.0001

Data Index: 1319157 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6149. Min Act: -0.0001

Data Index: 654532 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6446. Min Act: -0.0001

Data Index: 175131 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7017. Min Act: -0.0001

Data Index: 409017 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7235. Min Act: -0.0001

Data Index: 340112 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7020. Min Act: -0.0001

Data Index: 141453 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6374. Min Act: -0.0001

Data Index: 1319281 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6698. Min Act: -0.0001

Data Index: 694358 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6615. Min Act: -0.0001

Data Index: 844320 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6615. Min Act: -0.0001

Data Index: 274203 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6615. Min Act: -0.0001

Data Index: 5816 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6615. Min Act: -0.0001

Data Index: 618310 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6615. Min Act: -0.0001

Data Index: 1140790 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6350. Min Act: -0.0001

Data Index: 1055285 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6680. Min Act: -0.0001

Data Index: 1298974 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7193. Min Act: -0.0001

Data Index: 595710 (C4 (Web Text))

Max Activating Token Index: 285