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

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

Neuron 3468 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.9043. Min Act: -0.0000

Data Index: 793876 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.8773. Min Act: -0.0000

Data Index: 17112 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.6247. Min Act: -0.0000

Data Index: 1031709 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.4663. Min Act: -0.0000

Data Index: 227452 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.7009. Min Act: -0.0000

Data Index: 698883 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.6833. Min Act: -0.0000

Data Index: 762102 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.6605. Min Act: -0.0000

Data Index: 588905 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.6568. Min Act: -0.0000

Data Index: 474724 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.4964. Min Act: -0.0000

Data Index: 912491 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.6158. Min Act: -0.0000

Data Index: 632098 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.4913. Min Act: -0.0000

Data Index: 1356546 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.5889. Min Act: -0.0000

Data Index: 141702 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.7150. Min Act: -0.0001

Data Index: 1289347 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.5659. Min Act: -0.0000

Data Index: 954539 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.5443. Min Act: -0.0000

Data Index: 779198 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.5307. Min Act: -0.0000

Data Index: 295454 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.3980. Min Act: -0.0000

Data Index: 239271 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.4963. Min Act: -0.0000

Data Index: 1333074 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.3699. Min Act: -0.0000

Data Index: 542430 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 2.9043. Min Range: -2.9043

Max Act: 2.4960. Min Act: -0.0000

Data Index: 782724 (C4 (Web Text))

Max Activating Token Index: 376