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

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

Neuron 1115 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.4473. Min Act: -0.0000

Data Index: 572336 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.4672. Min Act: -0.0001

Data Index: 1221243 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.4838. Min Act: -0.0001

Data Index: 969555 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.4149. Min Act: -0.0000

Data Index: 247256 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.4172. Min Act: -0.0001

Data Index: 852204 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.4086. Min Act: -0.0001

Data Index: 189061 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3882. Min Act: -0.0001

Data Index: 137326 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.4291. Min Act: -0.0001

Data Index: 656649 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3735. Min Act: -0.0001

Data Index: 92467 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3589. Min Act: -0.0001

Data Index: 723494 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3839. Min Act: -0.0001

Data Index: 849006 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3419. Min Act: -0.0000

Data Index: 686391 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3626. Min Act: -0.0001

Data Index: 1093923 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3750. Min Act: -0.0001

Data Index: 348987 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3441. Min Act: -0.0001

Data Index: 193858 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3328. Min Act: -0.0000

Data Index: 311557 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3068. Min Act: -0.0000

Data Index: 1213386 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3400. Min Act: -0.0000

Data Index: 583405 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3281. Min Act: -0.0000

Data Index: 855410 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3302. Min Act: -0.0001

Data Index: 147862 (C4 (Web Text))

Max Activating Token Index: 28