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

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

Neuron 3757 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: 1.7870. Min Range: -1.7870

Max Act: 1.6162. Min Act: -0.0000

Data Index: 432471 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.7870. Min Act: -0.0000

Data Index: 1054177 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.5073. Min Act: -0.0000

Data Index: 314568 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.5923. Min Act: -0.0000

Data Index: 308579 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.5765. Min Act: -0.0000

Data Index: 191789 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.4363. Min Act: -0.0000

Data Index: 42276 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.4486. Min Act: -0.0000

Data Index: 884898 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.4673. Min Act: -0.0000

Data Index: 1142533 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.2477. Min Act: -0.0000

Data Index: 55567 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.3259. Min Act: -0.0000

Data Index: 11417 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.0384. Min Act: -0.0000

Data Index: 1287834 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.2409. Min Act: -0.0000

Data Index: 489996 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.2420. Min Act: -0.0000

Data Index: 986257 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.1376. Min Act: -0.0000

Data Index: 744141 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.1298. Min Act: -0.0000

Data Index: 195784 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.1047. Min Act: 0.0000

Data Index: 594433 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.0956. Min Act: -0.0000

Data Index: 296570 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.0739. Min Act: -0.0000

Data Index: 1159913 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.0771. Min Act: -0.0000

Data Index: 448153 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 1.7870. Min Range: -1.7870

Max Act: 1.0611. Min Act: -0.0000

Data Index: 240326 (C4 (Web Text))

Max Activating Token Index: 175