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

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

Neuron 342 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.3695. Min Act: -0.0000

Data Index: 45326 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.3005. Min Act: -0.0000

Data Index: 378612 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.2612. Min Act: -0.0000

Data Index: 624943 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.2470. Min Act: -0.0000

Data Index: 1431382 (Python Code)

Max Activating Token Index: 123

Text #4

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.1471. Min Act: -0.0000

Data Index: 810814 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.1730. Min Act: -0.0000

Data Index: 173478 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.1176. Min Act: -0.0000

Data Index: 1356583 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.2005. Min Act: -0.0000

Data Index: 1499598 (Python Code)

Max Activating Token Index: 985

Text #8

Max Range: 1.3695. Min Range: -1.3695

Max Act: 0.9115. Min Act: -0.0000

Data Index: 85381 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0381. Min Act: -0.0000

Data Index: 1257677 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0667. Min Act: -0.0001

Data Index: 945071 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0714. Min Act: -0.0000

Data Index: 694052 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0960. Min Act: -0.0000

Data Index: 1304148 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0681. Min Act: -0.0000

Data Index: 488688 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0369. Min Act: -0.0001

Data Index: 997345 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0967. Min Act: -0.0000

Data Index: 999877 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0196. Min Act: -0.0000

Data Index: 747503 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0466. Min Act: -0.0000

Data Index: 425374 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 1.3695. Min Range: -1.3695

Max Act: 1.0654. Min Act: -0.0000

Data Index: 1510082 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 1.3695. Min Range: -1.3695

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1023356 (C4 (Web Text))

Max Activating Token Index: 1008