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

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

Neuron 5088 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1138. Min Range: -2.1138

Max Act: 2.1138. Min Act: -0.0000

Data Index: 1043895 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.7439. Min Act: -0.0000

Data Index: 294807 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.5866. Min Act: -0.0000

Data Index: 1262733 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.4408. Min Act: -0.0000

Data Index: 350928 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.4003. Min Act: -0.0000

Data Index: 1009857 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.3225. Min Act: -0.0000

Data Index: 919204 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.3645. Min Act: -0.0000

Data Index: 1039673 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.2278. Min Act: -0.0000

Data Index: 187952 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.2278. Min Act: -0.0000

Data Index: 1001622 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.2820. Min Act: -0.0000

Data Index: 341109 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.2298. Min Act: -0.0000

Data Index: 492726 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.0421. Min Act: -0.0000

Data Index: 1164136 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.2916. Min Act: -0.0000

Data Index: 783295 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.2386. Min Act: -0.0000

Data Index: 1042725 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.2572. Min Act: -0.0000

Data Index: 814185 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.2047. Min Act: -0.0000

Data Index: 469757 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.2019. Min Act: -0.0000

Data Index: 743889 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.1666. Min Act: -0.0000

Data Index: 448487 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.1578. Min Act: -0.0000

Data Index: 42323 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 2.1138. Min Range: -2.1138

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1179751 (C4 (Web Text))

Max Activating Token Index: 819