Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1780 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3476. Min Act: -0.0001

Data Index: 977581 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3475. Min Act: -0.0001

Data Index: 475656 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3573. Min Act: -0.0001

Data Index: 1003370 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3531. Min Act: -0.0001

Data Index: 939061 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3384. Min Act: -0.0001

Data Index: 295217 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3270. Min Act: -0.0001

Data Index: 761568 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3508. Min Act: -0.0001

Data Index: 767773 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3604. Min Act: -0.0001

Data Index: 675491 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3385. Min Act: -0.0001

Data Index: 739076 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3369. Min Act: -0.0001

Data Index: 185975 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3476. Min Act: -0.0001

Data Index: 312846 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3487. Min Act: -0.0001

Data Index: 1136783 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3599. Min Act: -0.0001

Data Index: 1009204 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3221. Min Act: -0.0001

Data Index: 92845 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3447. Min Act: -0.0001

Data Index: 45099 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3321. Min Act: -0.0001

Data Index: 1011296 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3306. Min Act: -0.0001

Data Index: 946780 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3297. Min Act: -0.0001

Data Index: 777357 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3402. Min Act: -0.0001

Data Index: 321317 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.3604. Min Range: -0.3604

Max Act: 0.3261. Min Act: -0.0001

Data Index: 755091 (C4 (Web Text))

Max Activating Token Index: 205