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

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

Neuron 3311 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.5596. Min Act: -0.0001

Data Index: 1989 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.4222. Min Act: -0.0001

Data Index: 472613 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3569. Min Act: -0.0001

Data Index: 221926 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3963. Min Act: -0.0001

Data Index: 620577 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3709. Min Act: -0.0001

Data Index: 329648 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3903. Min Act: -0.0001

Data Index: 1041692 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3622. Min Act: -0.0001

Data Index: 1056368 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3700. Min Act: -0.0001

Data Index: 159986 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3513. Min Act: -0.0001

Data Index: 346713 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3290. Min Act: -0.0001

Data Index: 829623 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3352. Min Act: -0.0000

Data Index: 602834 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3345. Min Act: -0.0001

Data Index: 875972 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3320. Min Act: -0.0001

Data Index: 1099995 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3357. Min Act: -0.0001

Data Index: 940459 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3137. Min Act: -0.0001

Data Index: 34644 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3336. Min Act: -0.0001

Data Index: 1000890 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3324. Min Act: -0.0001

Data Index: 458232 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3291. Min Act: -0.0001

Data Index: 447975 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3302. Min Act: -0.0001

Data Index: 789695 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.5596. Min Range: -0.5596

Max Act: 0.3416. Min Act: -0.0001

Data Index: 544177 (C4 (Web Text))

Max Activating Token Index: 481