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

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

Neuron 3625 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.3043. Min Act: -0.0002

Data Index: 823412 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2828. Min Act: -0.0002

Data Index: 988273 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2680. Min Act: -0.0002

Data Index: 630177 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2563. Min Act: -0.0002

Data Index: 456301 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2543. Min Act: -0.0002

Data Index: 314439 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2499. Min Act: -0.0002

Data Index: 1207368 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2468. Min Act: -0.0002

Data Index: 1119716 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2642. Min Act: -0.0002

Data Index: 703955 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2329. Min Act: -0.0002

Data Index: 1297557 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2591. Min Act: -0.0002

Data Index: 1068457 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2263. Min Act: -0.0002

Data Index: 819661 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2360. Min Act: -0.0002

Data Index: 1344013 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2623. Min Act: -0.0002

Data Index: 1339619 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2269. Min Act: -0.0002

Data Index: 920643 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2459. Min Act: -0.0002

Data Index: 1348047 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2374. Min Act: -0.0002

Data Index: 1150862 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2418. Min Act: -0.0002

Data Index: 207364 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2344. Min Act: -0.0002

Data Index: 52385 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.2314. Min Act: -0.0002

Data Index: 1176443 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.3043. Min Range: -0.3043

Max Act: 0.1960. Min Act: -0.0002

Data Index: 1011487 (C4 (Web Text))

Max Activating Token Index: 761