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

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

Neuron 1234 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.9096. Min Act: -0.0000

Data Index: 992445 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7898. Min Act: -0.0000

Data Index: 147821 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7417. Min Act: 0.0001

Data Index: 1282122 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7684. Min Act: 0.0001

Data Index: 716903 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1212182 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7400. Min Act: 0.0001

Data Index: 831257 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7605. Min Act: 0.0001

Data Index: 721521 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6979. Min Act: 0.0001

Data Index: 237610 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6622. Min Act: 0.0001

Data Index: 875876 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6643. Min Act: 0.0001

Data Index: 119263 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6290. Min Act: 0.0001

Data Index: 1064461 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6660. Min Act: 0.0001

Data Index: 1146946 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6111. Min Act: 0.0001

Data Index: 106507 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6280. Min Act: -0.0000

Data Index: 582979 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6074. Min Act: -0.0000

Data Index: 801412 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6202. Min Act: -0.0000

Data Index: 254592 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6401. Min Act: -0.0000

Data Index: 193112 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6161. Min Act: 0.0001

Data Index: 559724 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.5915. Min Act: -0.0000

Data Index: 484327 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6129. Min Act: -0.0000

Data Index: 1234901 (C4 (Web Text))

Max Activating Token Index: 356