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

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

Neuron 1993 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.3093. Min Act: -0.0004

Data Index: 970493 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2291. Min Act: -0.0003

Data Index: 819225 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2255. Min Act: -0.0003

Data Index: 629331 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2217. Min Act: -0.0003

Data Index: 759002 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2169. Min Act: -0.0003

Data Index: 638229 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2224. Min Act: -0.0003

Data Index: 525265 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2197. Min Act: -0.0003

Data Index: 824745 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2050. Min Act: -0.0003

Data Index: 691980 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2113. Min Act: -0.0003

Data Index: 717158 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2031. Min Act: -0.0003

Data Index: 380785 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2086. Min Act: -0.0003

Data Index: 795228 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.1992. Min Act: -0.0003

Data Index: 843765 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2028. Min Act: -0.0003

Data Index: 1168582 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.1960. Min Act: -0.0003

Data Index: 1056898 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.2077. Min Act: -0.0003

Data Index: 743286 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.1995. Min Act: -0.0003

Data Index: 540372 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.1970. Min Act: -0.0003

Data Index: 937717 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.1965. Min Act: -0.0003

Data Index: 331377 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.1899. Min Act: -0.0003

Data Index: 41157 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 0.3093. Min Range: -0.3093

Max Act: 0.1881. Min Act: -0.0003

Data Index: 1167908 (C4 (Web Text))

Max Activating Token Index: 543