Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2448 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.4774. Min Act: -0.0001

Data Index: 1052129 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.4747. Min Act: -0.0000

Data Index: 686820 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.4635. Min Act: -0.0000

Data Index: 60337 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.4366. Min Act: -0.0000

Data Index: 658250 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.4192. Min Act: -0.0001

Data Index: 493435 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.4325. Min Act: -0.0000

Data Index: 840444 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.4033. Min Act: -0.0001

Data Index: 747877 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1085208 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.4055. Min Act: -0.0000

Data Index: 836406 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.4019. Min Act: -0.0000

Data Index: 294277 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3884. Min Act: -0.0000

Data Index: 131145 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3828. Min Act: -0.0000

Data Index: 153338 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3946. Min Act: -0.0000

Data Index: 1069586 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3805. Min Act: -0.0000

Data Index: 270299 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3890. Min Act: -0.0001

Data Index: 1243296 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3775. Min Act: -0.0001

Data Index: 1011382 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3889. Min Act: -0.0000

Data Index: 832092 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3874. Min Act: -0.0000

Data Index: 1028008 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3879. Min Act: -0.0000

Data Index: 369854 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1248603 (C4 (Web Text))

Max Activating Token Index: 65