Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1035 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0184. Min Act: -0.0005

Data Index: 300081 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0164. Min Act: -0.0005

Data Index: 835397 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0155. Min Act: -0.0006

Data Index: 348561 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0159. Min Act: -0.0005

Data Index: 935749 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0149. Min Act: -0.0005

Data Index: 881361 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0155. Min Act: -0.0006

Data Index: 765496 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0152. Min Act: -0.0005

Data Index: 265684 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0152. Min Act: -0.0006

Data Index: 922469 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0151. Min Act: -0.0005

Data Index: 255127 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0147. Min Act: -0.0005

Data Index: 1272313 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0147. Min Act: -0.0005

Data Index: 113978 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0147. Min Act: -0.0005

Data Index: 797491 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0145. Min Act: -0.0005

Data Index: 1304104 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1293952 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0146. Min Act: -0.0005

Data Index: 257424 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0148. Min Act: -0.0006

Data Index: 329285 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0145. Min Act: -0.0006

Data Index: 831307 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0144. Min Act: -0.0006

Data Index: 812965 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0144. Min Act: -0.0005

Data Index: 823234 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.0184. Min Range: -0.0184

Max Act: 0.0143. Min Act: -0.0005

Data Index: 713043 (C4 (Web Text))

Max Activating Token Index: 573