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

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

Neuron 2425 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1207671 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.7644. Min Act: -0.0000

Data Index: 513143 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.6867. Min Act: -0.0001

Data Index: 266398 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.6628. Min Act: -0.0000

Data Index: 382021 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.6664. Min Act: -0.0000

Data Index: 593611 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1199926 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5985. Min Act: -0.0000

Data Index: 709553 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5790. Min Act: -0.0000

Data Index: 806282 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5448. Min Act: -0.0000

Data Index: 766793 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5038. Min Act: -0.0001

Data Index: 1212500 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5454. Min Act: -0.0000

Data Index: 845796 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5253. Min Act: -0.0001

Data Index: 253198 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1142254 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5552. Min Act: -0.0000

Data Index: 208915 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5515. Min Act: -0.0000

Data Index: 341414 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1145287 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5231. Min Act: -0.0000

Data Index: 288116 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5395. Min Act: -0.0001

Data Index: 780667 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5205. Min Act: -0.0000

Data Index: 853206 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5388. Min Act: -0.0001

Data Index: 75695 (C4 (Web Text))

Max Activating Token Index: 709