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

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

Neuron 5065 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.7138. Min Act: -0.0002

Data Index: 1302996 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.6958. Min Act: -0.0002

Data Index: 1230051 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.7114. Min Act: -0.0002

Data Index: 1355288 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.6809. Min Act: -0.0002

Data Index: 1307075 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.7026. Min Act: -0.0002

Data Index: 431428 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.5118. Min Act: -0.0002

Data Index: 807009 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.5965. Min Act: -0.0002

Data Index: 671360 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.5717. Min Act: -0.0002

Data Index: 129329 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.5721. Min Act: -0.0002

Data Index: 858833 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.6305. Min Act: -0.0002

Data Index: 248518 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.6661. Min Act: -0.0002

Data Index: 800849 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.6349. Min Act: -0.0002

Data Index: 143766 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.5845. Min Act: -0.0002

Data Index: 1281032 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.5916. Min Act: -0.0002

Data Index: 682805 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.6026. Min Act: -0.0002

Data Index: 1046194 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.5805. Min Act: -0.0002

Data Index: 788181 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.6177. Min Act: -0.0002

Data Index: 1139900 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.6154. Min Act: -0.0002

Data Index: 346188 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.5982. Min Act: -0.0002

Data Index: 389157 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.7138. Min Range: -0.7138

Max Act: 0.5872. Min Act: -0.0002

Data Index: 99970 (C4 (Web Text))

Max Activating Token Index: 420