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

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

Neuron 1935 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.6176. Min Act: -0.0001

Data Index: 261615 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5972. Min Act: -0.0001

Data Index: 75154 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5754. Min Act: -0.0001

Data Index: 719638 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5819. Min Act: -0.0001

Data Index: 267578 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5785. Min Act: -0.0001

Data Index: 341032 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5935. Min Act: -0.0001

Data Index: 1333597 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5432. Min Act: -0.0001

Data Index: 43890 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5431. Min Act: -0.0001

Data Index: 714275 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5648. Min Act: -0.0001

Data Index: 923597 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5291. Min Act: -0.0001

Data Index: 54442 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5047. Min Act: -0.0001

Data Index: 1129953 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5456. Min Act: -0.0001

Data Index: 68500 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.4883. Min Act: -0.0001

Data Index: 452594 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5564. Min Act: -0.0001

Data Index: 1038645 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5435. Min Act: -0.0001

Data Index: 75073 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5600. Min Act: -0.0001

Data Index: 523870 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5188. Min Act: -0.0001

Data Index: 207289 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.5189. Min Act: -0.0001

Data Index: 867013 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.4961. Min Act: -0.0001

Data Index: 127629 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.6176. Min Range: -0.6176

Max Act: 0.4993. Min Act: -0.0001

Data Index: 143163 (C4 (Web Text))

Max Activating Token Index: 569