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

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

Neuron 3754 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.5809. Min Act: -0.0000

Data Index: 359769 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.4400. Min Act: -0.0000

Data Index: 501397 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1281652 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1278395 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.3797. Min Act: -0.0000

Data Index: 388248 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.4063. Min Act: -0.0000

Data Index: 712577 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.3765. Min Act: -0.0000

Data Index: 117405 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.4283. Min Act: -0.0000

Data Index: 453943 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1223563 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.3810. Min Act: -0.0000

Data Index: 496729 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.3945. Min Act: -0.0000

Data Index: 206973 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.3616. Min Act: -0.0000

Data Index: 20502 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.3620. Min Act: -0.0000

Data Index: 230528 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.3577. Min Act: -0.0000

Data Index: 1172163 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1024368 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.3567. Min Act: -0.0000

Data Index: 676542 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.3455. Min Act: -0.0000

Data Index: 576432 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.3417. Min Act: -0.0000

Data Index: 255836 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.3646. Min Act: -0.0000

Data Index: 1250248 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.5809. Min Range: -0.5809

Max Act: 0.3332. Min Act: -0.0000

Data Index: 388916 (C4 (Web Text))

Max Activating Token Index: 242