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

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

Neuron 2950 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2359. Min Act: -0.0003

Data Index: 50311 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.2273. Min Act: -0.0003

Data Index: 1340514 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1959. Min Act: -0.0003

Data Index: 1256297 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1899. Min Act: -0.0003

Data Index: 1091672 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1809. Min Act: -0.0003

Data Index: 108278 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1791. Min Act: -0.0003

Data Index: 1314594 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1788. Min Act: -0.0002

Data Index: 370056 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1787. Min Act: -0.0003

Data Index: 61571 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1731. Min Act: -0.0003

Data Index: 448510 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1670. Min Act: -0.0003

Data Index: 839682 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1714. Min Act: -0.0003

Data Index: 294631 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1712. Min Act: -0.0003

Data Index: 1101034 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1704. Min Act: -0.0003

Data Index: 1327895 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1693. Min Act: -0.0002

Data Index: 28470 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1682. Min Act: -0.0003

Data Index: 959857 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1726. Min Act: -0.0003

Data Index: 419568 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1726. Min Act: -0.0002

Data Index: 755299 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1661. Min Act: -0.0003

Data Index: 828743 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1653. Min Act: -0.0002

Data Index: 1030171 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.2359. Min Range: -0.2359

Max Act: 0.1632. Min Act: -0.0003

Data Index: 1089638 (C4 (Web Text))

Max Activating Token Index: 870