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

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

Neuron 3983 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: 1.5578. Min Range: -1.5578

Max Act: 1.5271. Min Act: -0.0000

Data Index: 851333 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.5578. Min Act: -0.0000

Data Index: 1258657 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.5322. Min Act: -0.0000

Data Index: 646388 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.5205. Min Act: -0.0000

Data Index: 394714 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.4670. Min Act: -0.0000

Data Index: 598234 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.4989. Min Act: -0.0000

Data Index: 211200 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.4882. Min Act: -0.0000

Data Index: 906764 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.4257. Min Act: -0.0000

Data Index: 932869 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.4048. Min Act: -0.0000

Data Index: 893943 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3911. Min Act: -0.0000

Data Index: 274589 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3813. Min Act: -0.0000

Data Index: 127816 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3895. Min Act: -0.0000

Data Index: 479556 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3291. Min Act: -0.0000

Data Index: 383999 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.4096. Min Act: -0.0000

Data Index: 241737 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3382. Min Act: -0.0000

Data Index: 949177 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.4441. Min Act: -0.0000

Data Index: 1243144 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3955. Min Act: -0.0000

Data Index: 1181434 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3543. Min Act: -0.0000

Data Index: 729050 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.3827. Min Act: -0.0000

Data Index: 286976 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 1.5578. Min Range: -1.5578

Max Act: 1.2770. Min Act: -0.0000

Data Index: 769700 (C4 (Web Text))

Max Activating Token Index: 550