Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 910 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.3128. Min Act: -0.0002

Data Index: 1304818 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2719. Min Act: -0.0002

Data Index: 538066 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2779. Min Act: -0.0003

Data Index: 807598 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2623. Min Act: -0.0002

Data Index: 239236 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2615. Min Act: -0.0003

Data Index: 286278 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2556. Min Act: -0.0003

Data Index: 1329326 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2682. Min Act: -0.0002

Data Index: 638089 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2581. Min Act: -0.0003

Data Index: 379859 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2484. Min Act: -0.0002

Data Index: 1144397 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2579. Min Act: -0.0003

Data Index: 1089141 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2581. Min Act: -0.0003

Data Index: 1279582 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2387. Min Act: -0.0002

Data Index: 947224 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2421. Min Act: -0.0003

Data Index: 818573 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2446. Min Act: -0.0003

Data Index: 1335080 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2447. Min Act: -0.0003

Data Index: 771006 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2508. Min Act: -0.0003

Data Index: 152148 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2389. Min Act: -0.0002

Data Index: 1240160 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2364. Min Act: -0.0002

Data Index: 1397003 (Python Code)

Max Activating Token Index: 706

Text #18

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2347. Min Act: -0.0004

Data Index: 570257 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.3128. Min Range: -0.3128

Max Act: 0.2389. Min Act: -0.0003

Data Index: 1083184 (C4 (Web Text))

Max Activating Token Index: 100