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

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

Neuron 4079 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: 0.5920. Min Range: -0.5920

Max Act: 0.5920. Min Act: -0.0000

Data Index: 305379 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.5391. Min Act: -0.0000

Data Index: 266107 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1544050 (Python Code)

Max Activating Token Index: 164

Text #3

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3891. Min Act: -0.0000

Data Index: 637968 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1481002 (Python Code)

Max Activating Token Index: 225

Text #5

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3602. Min Act: -0.0000

Data Index: 302773 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3725. Min Act: -0.0000

Data Index: 1303385 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3656. Min Act: -0.0000

Data Index: 606969 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3506. Min Act: -0.0000

Data Index: 84407 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3362. Min Act: -0.0000

Data Index: 661674 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3173. Min Act: -0.0000

Data Index: 712654 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3380. Min Act: -0.0000

Data Index: 259937 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3477. Min Act: -0.0000

Data Index: 904654 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3262. Min Act: -0.0000

Data Index: 1651786 (Python Code)

Max Activating Token Index: 427

Text #14

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1513798 (Python Code)

Max Activating Token Index: 91

Text #15

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3072. Min Act: -0.0000

Data Index: 1271725 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3111. Min Act: -0.0000

Data Index: 1315151 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1458896 (Python Code)

Max Activating Token Index: 244

Text #18

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1518966 (Python Code)

Max Activating Token Index: 94

Text #19

Max Range: 0.5920. Min Range: -0.5920

Max Act: 0.2862. Min Act: -0.0000

Data Index: 201057 (C4 (Web Text))

Max Activating Token Index: 888