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

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

Neuron 673 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.5063. Min Act: -0.0000

Data Index: 206260 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.4688. Min Act: -0.0000

Data Index: 445377 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.4296. Min Act: 0.0000

Data Index: 772659 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3952. Min Act: -0.0000

Data Index: 639662 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3602. Min Act: -0.0000

Data Index: 1270021 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1062543 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1039449 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3680. Min Act: -0.0000

Data Index: 20734 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3659. Min Act: -0.0000

Data Index: 47131 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3563. Min Act: -0.0000

Data Index: 761259 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1235378 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3531. Min Act: -0.0000

Data Index: 824039 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3513. Min Act: -0.0000

Data Index: 528572 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3611. Min Act: -0.0000

Data Index: 92560 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3254. Min Act: -0.0000

Data Index: 745349 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3470. Min Act: -0.0000

Data Index: 28373 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3479. Min Act: -0.0000

Data Index: 122835 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3379. Min Act: -0.0000

Data Index: 706144 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3557. Min Act: -0.0000

Data Index: 469607 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.5063. Min Range: -0.5063

Max Act: 0.3283. Min Act: -0.0000

Data Index: 788366 (C4 (Web Text))

Max Activating Token Index: 401