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

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

Neuron 4988 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1197. Min Range: -3.1197

Max Act: 3.1197. Min Act: -0.0000

Data Index: 1008969 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.7355. Min Act: -0.0000

Data Index: 11809 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.8965. Min Act: -0.0000

Data Index: 734367 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.6043. Min Act: -0.0000

Data Index: 964538 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.8262. Min Act: -0.0000

Data Index: 1220626 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.8723. Min Act: -0.0000

Data Index: 854071 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.6840. Min Act: -0.0000

Data Index: 728209 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.7781. Min Act: -0.0000

Data Index: 308448 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.7316. Min Act: -0.0000

Data Index: 939526 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.7203. Min Act: -0.0000

Data Index: 323570 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.8680. Min Act: -0.0000

Data Index: 1075455 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.5679. Min Act: -0.0000

Data Index: 861761 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.6796. Min Act: -0.0000

Data Index: 643635 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.5444. Min Act: -0.0000

Data Index: 1056418 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.5838. Min Act: -0.0000

Data Index: 698797 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.7294. Min Act: -0.0000

Data Index: 788716 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.5936. Min Act: -0.0000

Data Index: 1164741 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.6051. Min Act: -0.0000

Data Index: 1204893 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.5903. Min Act: -0.0000

Data Index: 38366 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.4363. Min Act: -0.0000

Data Index: 114824 (C4 (Web Text))

Max Activating Token Index: 964