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

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

Neuron 2844 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2220. Min Act: -0.0001

Data Index: 1150403 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2874. Min Act: -0.0001

Data Index: 1357543 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2677. Min Act: -0.0001

Data Index: 1311988 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.2032. Min Act: -0.0001

Data Index: 1267081 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1725. Min Act: -0.0001

Data Index: 548158 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1603. Min Act: -0.0001

Data Index: 906833 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1197. Min Act: -0.0001

Data Index: 163295 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1205. Min Act: -0.0001

Data Index: 31636 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.0814. Min Act: -0.0001

Data Index: 543266 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1444. Min Act: -0.0001

Data Index: 1287112 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.0704. Min Act: -0.0001

Data Index: 385395 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.1631. Min Act: -0.0001

Data Index: 1138475 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.0628. Min Act: -0.0001

Data Index: 847460 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.0380. Min Act: -0.0001

Data Index: 528279 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.0027. Min Act: -0.0001

Data Index: 282848 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.0592. Min Act: -0.0001

Data Index: 454508 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.0622. Min Act: -0.0001

Data Index: 295047 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 1.2874. Min Range: -1.2874

Max Act: 0.9915. Min Act: -0.0001

Data Index: 861820 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.0437. Min Act: -0.0001

Data Index: 1588485 (Python Code)

Max Activating Token Index: 398

Text #19

Max Range: 1.2874. Min Range: -1.2874

Max Act: 1.0180. Min Act: -0.0001

Data Index: 142144 (C4 (Web Text))

Max Activating Token Index: 932