Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 697 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.4178. Min Act: -0.0001

Data Index: 1302065 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3240. Min Act: -0.0001

Data Index: 990036 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3789. Min Act: -0.0001

Data Index: 353771 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3729. Min Act: -0.0001

Data Index: 321082 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3401. Min Act: -0.0001

Data Index: 504400 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3255. Min Act: -0.0001

Data Index: 1010873 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3215. Min Act: -0.0001

Data Index: 974013 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3238. Min Act: -0.0001

Data Index: 279409 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.2893. Min Act: -0.0001

Data Index: 633242 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.2892. Min Act: -0.0001

Data Index: 1232512 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3139. Min Act: -0.0001

Data Index: 1318690 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3059. Min Act: -0.0001

Data Index: 234829 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3095. Min Act: -0.0001

Data Index: 277629 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3260. Min Act: -0.0001

Data Index: 60112 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.2917. Min Act: -0.0001

Data Index: 439067 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3121. Min Act: -0.0001

Data Index: 248243 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3027. Min Act: -0.0001

Data Index: 498268 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.2889. Min Act: -0.0001

Data Index: 864649 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.3149. Min Act: -0.0001

Data Index: 347207 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.4178. Min Range: -0.4178

Max Act: 0.2542. Min Act: -0.0001

Data Index: 178197 (C4 (Web Text))

Max Activating Token Index: 922