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

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

Neuron 4476 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.5008. Min Act: -0.0002

Data Index: 429458 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4677. Min Act: -0.0002

Data Index: 100728 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4311. Min Act: -0.0002

Data Index: 1166758 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4501. Min Act: -0.0002

Data Index: 256626 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4353. Min Act: -0.0002

Data Index: 362235 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4267. Min Act: -0.0002

Data Index: 985990 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4497. Min Act: -0.0002

Data Index: 1304152 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4142. Min Act: -0.0002

Data Index: 379480 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4280. Min Act: -0.0002

Data Index: 333627 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4077. Min Act: -0.0002

Data Index: 338473 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.3965. Min Act: -0.0002

Data Index: 412572 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.3833. Min Act: -0.0002

Data Index: 274299 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.3573. Min Act: -0.0002

Data Index: 164450 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.3664. Min Act: -0.0002

Data Index: 1038144 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.3627. Min Act: -0.0002

Data Index: 16969 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.3676. Min Act: -0.0002

Data Index: 984770 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.3650. Min Act: -0.0002

Data Index: 495667 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.3625. Min Act: -0.0002

Data Index: 1087637 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.3373. Min Act: -0.0002

Data Index: 436560 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.3359. Min Act: -0.0002

Data Index: 389508 (C4 (Web Text))

Max Activating Token Index: 419