Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5813 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.8978. Min Act: -0.0000

Data Index: 687808 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.7618. Min Act: -0.0000

Data Index: 379481 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.7311. Min Act: -0.0000

Data Index: 952111 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.5763. Min Act: -0.0000

Data Index: 649294 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1044393 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.5263. Min Act: -0.0000

Data Index: 872573 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.5414. Min Act: 0.0000

Data Index: 335735 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.5171. Min Act: -0.0000

Data Index: 97147 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.5108. Min Act: -0.0000

Data Index: 431546 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.4923. Min Act: -0.0000

Data Index: 781903 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.4572. Min Act: -0.0000

Data Index: 883975 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.4601. Min Act: -0.0000

Data Index: 850936 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.4762. Min Act: -0.0000

Data Index: 844824 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.4465. Min Act: -0.0000

Data Index: 849002 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.4593. Min Act: -0.0000

Data Index: 534565 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1080986 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1145727 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.4113. Min Act: -0.0000

Data Index: 671308 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.3928. Min Act: -0.0000

Data Index: 904973 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.8978. Min Range: -0.8978

Max Act: 0.4395. Min Act: -0.0000

Data Index: 285024 (C4 (Web Text))

Max Activating Token Index: 647