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

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

Neuron 3393 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0981. Min Act: -0.0002

Data Index: 890593 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0964. Min Act: -0.0001

Data Index: 748052 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0933. Min Act: -0.0001

Data Index: 1284049 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0923. Min Act: -0.0002

Data Index: 258047 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0872. Min Act: -0.0001

Data Index: 685273 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0889. Min Act: -0.0001

Data Index: 61264 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0818. Min Act: -0.0002

Data Index: 343128 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0848. Min Act: -0.0002

Data Index: 308271 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1341751 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0878. Min Act: -0.0002

Data Index: 561507 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0877. Min Act: -0.0002

Data Index: 607332 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0869. Min Act: -0.0001

Data Index: 961129 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0896. Min Act: -0.0002

Data Index: 913340 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0860. Min Act: -0.0002

Data Index: 807488 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0855. Min Act: -0.0001

Data Index: 291967 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0846. Min Act: -0.0002

Data Index: 747642 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0815. Min Act: -0.0002

Data Index: 266230 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0874. Min Act: -0.0002

Data Index: 104272 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0843. Min Act: -0.0002

Data Index: 663651 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0795. Min Act: -0.0001

Data Index: 810165 (C4 (Web Text))

Max Activating Token Index: 680