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

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

Neuron 3708 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0895. Min Act: -0.0001

Data Index: 977951 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1177110 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0920. Min Act: -0.0001

Data Index: 1087493 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0861. Min Act: -0.0001

Data Index: 365064 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0867. Min Act: -0.0001

Data Index: 499832 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0732. Min Act: -0.0001

Data Index: 168925 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0804. Min Act: -0.0000

Data Index: 191990 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0794. Min Act: -0.0001

Data Index: 643036 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1348483 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1084303 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0699. Min Act: -0.0001

Data Index: 206951 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0783. Min Act: -0.0001

Data Index: 566618 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0739. Min Act: -0.0001

Data Index: 796753 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0696. Min Act: -0.0001

Data Index: 837290 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1349807 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1105796 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0714. Min Act: -0.0001

Data Index: 304343 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0677. Min Act: -0.0000

Data Index: 969288 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0674. Min Act: -0.0000

Data Index: 50562 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1117540 (C4 (Web Text))

Max Activating Token Index: 606