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

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

Neuron 5 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.8110. Min Act: -0.0001

Data Index: 777786 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.7349. Min Act: -0.0001

Data Index: 1292966 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.7669. Min Act: -0.0001

Data Index: 1316338 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.7391. Min Act: -0.0001

Data Index: 1320083 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.5566. Min Act: -0.0001

Data Index: 58048 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.7305. Min Act: -0.0001

Data Index: 1243004 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.6813. Min Act: -0.0001

Data Index: 637388 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.5490. Min Act: -0.0001

Data Index: 448567 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.6373. Min Act: -0.0001

Data Index: 286604 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.5404. Min Act: -0.0001

Data Index: 691906 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.5560. Min Act: -0.0001

Data Index: 561071 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.7983. Min Act: -0.0001

Data Index: 421902 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.4884. Min Act: -0.0001

Data Index: 380236 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.4444. Min Act: -0.0001

Data Index: 1299009 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.6368. Min Act: -0.0001

Data Index: 1266177 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.4495. Min Act: -0.0001

Data Index: 658621 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.4761. Min Act: -0.0001

Data Index: 1006833 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.5555. Min Act: -0.0001

Data Index: 845859 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.4412. Min Act: -0.0001

Data Index: 399566 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 1.8110. Min Range: -1.8110

Max Act: 1.6571. Min Act: -0.0001

Data Index: 1025136 (C4 (Web Text))

Max Activating Token Index: 173