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

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

Neuron 595 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: 2.9360. Min Range: -2.9360

Max Act: 2.9360. Min Act: -0.0000

Data Index: 39958 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 2.9360. Min Range: -2.9360

Max Act: 2.7537. Min Act: -0.0000

Data Index: 1308990 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 2.9360. Min Range: -2.9360

Max Act: 2.5185. Min Act: -0.0000

Data Index: 527236 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 2.9360. Min Range: -2.9360

Max Act: 2.4785. Min Act: -0.0000

Data Index: 1128947 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 2.9360. Min Range: -2.9360

Max Act: 2.2949. Min Act: -0.0000

Data Index: 870799 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 2.9360. Min Range: -2.9360

Max Act: 2.3920. Min Act: -0.0000

Data Index: 379044 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 2.9360. Min Range: -2.9360

Max Act: 2.2023. Min Act: -0.0000

Data Index: 877319 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 2.9360. Min Range: -2.9360

Max Act: 2.1025. Min Act: -0.0000

Data Index: 299384 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 2.9360. Min Range: -2.9360

Max Act: 2.0397. Min Act: -0.0000

Data Index: 331807 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 2.9360. Min Range: -2.9360

Max Act: 1.9215. Min Act: -0.0000

Data Index: 1134846 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 2.9360. Min Range: -2.9360

Max Act: 2.0138. Min Act: -0.0000

Data Index: 1022128 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 2.9360. Min Range: -2.9360

Max Act: 1.9028. Min Act: -0.0000

Data Index: 902793 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 2.9360. Min Range: -2.9360

Max Act: 1.7992. Min Act: -0.0000

Data Index: 192243 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 2.9360. Min Range: -2.9360

Max Act: 1.9676. Min Act: -0.0000

Data Index: 1073989 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 2.9360. Min Range: -2.9360

Max Act: 1.8692. Min Act: -0.0000

Data Index: 204220 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 2.9360. Min Range: -2.9360

Max Act: 1.9544. Min Act: -0.0000

Data Index: 1145754 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 2.9360. Min Range: -2.9360

Max Act: 1.8304. Min Act: -0.0000

Data Index: 520005 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 2.9360. Min Range: -2.9360

Max Act: 1.8464. Min Act: -0.0000

Data Index: 898612 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 2.9360. Min Range: -2.9360

Max Act: 1.7919. Min Act: -0.0000

Data Index: 1036619 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 2.9360. Min Range: -2.9360

Max Act: 1.7395. Min Act: -0.0000

Data Index: 789717 (C4 (Web Text))

Max Activating Token Index: 440