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

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

Neuron 4660 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: 2.5808. Min Range: -2.5808

Max Act: 2.5808. Min Act: -0.0000

Data Index: 736922 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 2.5808. Min Range: -2.5808

Max Act: 2.4706. Min Act: -0.0000

Data Index: 527181 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 2.5808. Min Range: -2.5808

Max Act: 2.1796. Min Act: -0.0000

Data Index: 1289807 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 2.5808. Min Range: -2.5808

Max Act: 2.3580. Min Act: -0.0000

Data Index: 1239735 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 2.5808. Min Range: -2.5808

Max Act: 2.1277. Min Act: -0.0000

Data Index: 875956 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 2.5808. Min Range: -2.5808

Max Act: 2.0200. Min Act: -0.0000

Data Index: 1254274 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 2.5808. Min Range: -2.5808

Max Act: 2.2340. Min Act: -0.0000

Data Index: 876965 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 2.5808. Min Range: -2.5808

Max Act: 2.2164. Min Act: -0.0000

Data Index: 1266420 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 2.5808. Min Range: -2.5808

Max Act: 2.2035. Min Act: -0.0000

Data Index: 715542 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 2.5808. Min Range: -2.5808

Max Act: 2.0686. Min Act: -0.0000

Data Index: 877266 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 2.5808. Min Range: -2.5808

Max Act: 2.0417. Min Act: -0.0000

Data Index: 552705 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 2.5808. Min Range: -2.5808

Max Act: 1.8308. Min Act: -0.0000

Data Index: 801177 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 2.5808. Min Range: -2.5808

Max Act: 1.8226. Min Act: -0.0000

Data Index: 236077 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 2.5808. Min Range: -2.5808

Max Act: 1.9101. Min Act: -0.0000

Data Index: 562042 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 2.5808. Min Range: -2.5808

Max Act: 2.0045. Min Act: -0.0000

Data Index: 895118 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 2.5808. Min Range: -2.5808

Max Act: 1.8818. Min Act: -0.0000

Data Index: 968828 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 2.5808. Min Range: -2.5808

Max Act: 1.8128. Min Act: -0.0000

Data Index: 949782 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 2.5808. Min Range: -2.5808

Max Act: 1.6785. Min Act: -0.0000

Data Index: 549590 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 2.5808. Min Range: -2.5808

Max Act: 1.7598. Min Act: -0.0000

Data Index: 1171830 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 2.5808. Min Range: -2.5808

Max Act: 1.7549. Min Act: -0.0000

Data Index: 571533 (C4 (Web Text))

Max Activating Token Index: 797