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

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

Neuron 833 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: 0.2619. Min Range: -0.2619

Max Act: 0.2619. Min Act: -0.0002

Data Index: 852537 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2543. Min Act: -0.0002

Data Index: 316250 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2284. Min Act: -0.0002

Data Index: 37493 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2274. Min Act: -0.0002

Data Index: 53657 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2497. Min Act: -0.0002

Data Index: 696504 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2069. Min Act: -0.0002

Data Index: 705031 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2018. Min Act: -0.0002

Data Index: 708205 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2354. Min Act: -0.0002

Data Index: 174389 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2098. Min Act: -0.0002

Data Index: 1116333 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2054. Min Act: -0.0002

Data Index: 489402 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2169. Min Act: -0.0002

Data Index: 1180279 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2128. Min Act: -0.0002

Data Index: 1326778 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2039. Min Act: -0.0002

Data Index: 735367 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2065. Min Act: -0.0002

Data Index: 226923 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2244. Min Act: -0.0002

Data Index: 245250 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1958. Min Act: -0.0002

Data Index: 25373 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.2058. Min Act: -0.0002

Data Index: 355867 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1759. Min Act: -0.0002

Data Index: 1082789 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1949. Min Act: -0.0002

Data Index: 1266534 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.2619. Min Range: -0.2619

Max Act: 0.1827. Min Act: -0.0002

Data Index: 709511 (C4 (Web Text))

Max Activating Token Index: 165