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

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

Neuron 1959 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: 1.4835. Min Range: -1.4835

Max Act: 1.1636. Min Act: -0.0002

Data Index: 880291 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 1.4835. Min Range: -1.4835

Max Act: 1.4835. Min Act: -0.0002

Data Index: 1284034 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 1.4835. Min Range: -1.4835

Max Act: 1.3621. Min Act: -0.0002

Data Index: 835850 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 1.4835. Min Range: -1.4835

Max Act: 1.2753. Min Act: -0.0002

Data Index: 808450 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 1.4835. Min Range: -1.4835

Max Act: 1.0173. Min Act: -0.0002

Data Index: 724717 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 1.4835. Min Range: -1.4835

Max Act: 0.9895. Min Act: -0.0002

Data Index: 561215 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 1.4835. Min Range: -1.4835

Max Act: 1.0827. Min Act: -0.0002

Data Index: 1002758 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 1.4835. Min Range: -1.4835

Max Act: 0.9791. Min Act: -0.0002

Data Index: 941511 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 1.4835. Min Range: -1.4835

Max Act: 0.9685. Min Act: -0.0002

Data Index: 674663 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 1.4835. Min Range: -1.4835

Max Act: 0.9175. Min Act: -0.0002

Data Index: 667202 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 1.4835. Min Range: -1.4835

Max Act: 0.9076. Min Act: -0.0002

Data Index: 160878 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 1.4835. Min Range: -1.4835

Max Act: 0.8978. Min Act: -0.0002

Data Index: 1088307 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 1.4835. Min Range: -1.4835

Max Act: 0.9808. Min Act: -0.0002

Data Index: 677802 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 1.4835. Min Range: -1.4835

Max Act: 0.9386. Min Act: -0.0002

Data Index: 1293868 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 1.4835. Min Range: -1.4835

Max Act: 0.9651. Min Act: -0.0002

Data Index: 665105 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 1.4835. Min Range: -1.4835

Max Act: 0.9242. Min Act: -0.0002

Data Index: 96046 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 1.4835. Min Range: -1.4835

Max Act: 1.0094. Min Act: -0.0002

Data Index: 366879 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 1.4835. Min Range: -1.4835

Max Act: 0.9455. Min Act: -0.0002

Data Index: 667503 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 1.4835. Min Range: -1.4835

Max Act: 0.9646. Min Act: -0.0002

Data Index: 243421 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 1.4835. Min Range: -1.4835

Max Act: 0.8508. Min Act: -0.0002

Data Index: 127116 (C4 (Web Text))

Max Activating Token Index: 72