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

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

Neuron 56 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0872. Min Range: -2.0872

Max Act: 2.0872. Min Act: -0.0000

Data Index: 1134334 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.6408. Min Act: -0.0000

Data Index: 744933 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.6436. Min Act: -0.0000

Data Index: 812908 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.6366. Min Act: -0.0000

Data Index: 1048164 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.4720. Min Act: -0.0000

Data Index: 698219 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.2547. Min Act: -0.0000

Data Index: 565902 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.4621. Min Act: -0.0000

Data Index: 991945 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.3754. Min Act: -0.0000

Data Index: 629279 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.2477. Min Act: -0.0000

Data Index: 566554 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.3821. Min Act: -0.0000

Data Index: 46656 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.2617. Min Act: -0.0000

Data Index: 1498394 (Python Code)

Max Activating Token Index: 381

Text #11

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.3305. Min Act: -0.0000

Data Index: 488040 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.2873. Min Act: -0.0000

Data Index: 106006 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.3202. Min Act: -0.0000

Data Index: 288607 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.2780. Min Act: -0.0000

Data Index: 1285248 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.2555. Min Act: -0.0000

Data Index: 357905 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.2528. Min Act: -0.0000

Data Index: 1254578 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.3056. Min Act: -0.0000

Data Index: 1019906 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.2479. Min Act: -0.0000

Data Index: 980114 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 2.0872. Min Range: -2.0872

Max Act: 1.2938. Min Act: -0.0000

Data Index: 503148 (C4 (Web Text))

Max Activating Token Index: 801