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

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

Neuron 2303 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: 0.0073. Min Range: -0.0073

Max Act: 0.0073. Min Act: -0.0003

Data Index: 254216 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0069. Min Act: -0.0003

Data Index: 145666 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1282569 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0061. Min Act: -0.0003

Data Index: 287289 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0060. Min Act: -0.0003

Data Index: 309873 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0057. Min Act: -0.0003

Data Index: 581055 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0056. Min Act: -0.0004

Data Index: 5474 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0055. Min Act: -0.0003

Data Index: 854270 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0056. Min Act: -0.0004

Data Index: 1153661 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0057. Min Act: -0.0003

Data Index: 952757 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1119825 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0054. Min Act: -0.0003

Data Index: 1105332 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0055. Min Act: -0.0003

Data Index: 374587 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0059. Min Act: -0.0003

Data Index: 521518 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0054. Min Act: -0.0003

Data Index: 18844 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0053. Min Act: -0.0003

Data Index: 730623 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0055. Min Act: -0.0003

Data Index: 174821 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0053. Min Act: -0.0003

Data Index: 990403 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0053. Min Act: -0.0003

Data Index: 671482 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0052. Min Act: -0.0003

Data Index: 70467 (C4 (Web Text))

Max Activating Token Index: 918