Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5256 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1113174 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.8209. Min Act: -0.0000

Data Index: 1062267 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.7701. Min Act: -0.0000

Data Index: 411419 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.7657. Min Act: -0.0000

Data Index: 461603 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.7979. Min Act: -0.0000

Data Index: 131433 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.7652. Min Act: -0.0000

Data Index: 710659 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.7084. Min Act: -0.0000

Data Index: 793385 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.7233. Min Act: -0.0000

Data Index: 548671 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.7231. Min Act: -0.0000

Data Index: 552140 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.7089. Min Act: -0.0000

Data Index: 881527 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.6942. Min Act: -0.0000

Data Index: 1291256 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1158100 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.6885. Min Act: -0.0000

Data Index: 1260097 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.6693. Min Act: -0.0000

Data Index: 385689 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1137798 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.6675. Min Act: -0.0000

Data Index: 102371 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1025530 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1173569 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1053878 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.8312. Min Range: -0.8312

Max Act: 0.6749. Min Act: -0.0000

Data Index: 332388 (C4 (Web Text))

Max Activating Token Index: 137