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

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

Neuron 3585 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: 5.8875. Min Range: -5.8875

Max Act: 5.8875. Min Act: -0.0001

Data Index: 1032037 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.7193. Min Act: -0.0001

Data Index: 376162 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.5113. Min Act: -0.0001

Data Index: 49742 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.4999. Min Act: -0.0001

Data Index: 348667 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.3373. Min Act: -0.0001

Data Index: 706402 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.3675. Min Act: -0.0001

Data Index: 1040049 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.3798. Min Act: -0.0001

Data Index: 440635 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.6924. Min Act: -0.0001

Data Index: 708244 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.3455. Min Act: -0.0001

Data Index: 796366 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.3572. Min Act: -0.0001

Data Index: 376780 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.3452. Min Act: -0.0001

Data Index: 466235 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.5116. Min Act: -0.0001

Data Index: 1170672 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.4901. Min Act: -0.0001

Data Index: 360726 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.3310. Min Act: -0.0001

Data Index: 4039 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.3250. Min Act: -0.0001

Data Index: 1019992 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.3013. Min Act: -0.0001

Data Index: 985971 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.2105. Min Act: -0.0001

Data Index: 1127538 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.5214. Min Act: -0.0001

Data Index: 387918 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.1518. Min Act: -0.0001

Data Index: 1331315 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 5.8875. Min Range: -5.8875

Max Act: 5.0059. Min Act: -0.0001

Data Index: 1221262 (C4 (Web Text))

Max Activating Token Index: 878