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

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

Neuron 3479 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.6031. Min Act: -0.0000

Data Index: 436212 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.5961. Min Act: -0.0000

Data Index: 833414 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.5606. Min Act: -0.0000

Data Index: 383981 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.5435. Min Act: -0.0000

Data Index: 409967 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4835. Min Act: -0.0000

Data Index: 735296 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.5067. Min Act: -0.0000

Data Index: 512498 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4438. Min Act: -0.0000

Data Index: 726879 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4702. Min Act: -0.0000

Data Index: 932455 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4483. Min Act: -0.0000

Data Index: 967522 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4392. Min Act: -0.0000

Data Index: 889377 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4490. Min Act: -0.0000

Data Index: 364028 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1352329 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4302. Min Act: -0.0000

Data Index: 184650 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4134. Min Act: -0.0000

Data Index: 311330 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4384. Min Act: -0.0000

Data Index: 286457 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4147. Min Act: -0.0000

Data Index: 214334 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.4189. Min Act: -0.0000

Data Index: 134155 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1083697 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.3865. Min Act: -0.0000

Data Index: 133420 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.6031. Min Range: -0.6031

Max Act: 0.3713. Min Act: -0.0000

Data Index: 943844 (C4 (Web Text))

Max Activating Token Index: 157