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

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

Neuron 5622 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4267. Min Act: -0.0000

Data Index: 236957 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1285376 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4715. Min Act: -0.0000

Data Index: 84450 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4339. Min Act: -0.0000

Data Index: 670437 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3893. Min Act: -0.0000

Data Index: 41930 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3830. Min Act: -0.0000

Data Index: 446194 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3852. Min Act: -0.0000

Data Index: 797706 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3638. Min Act: -0.0000

Data Index: 325225 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3575. Min Act: -0.0000

Data Index: 541181 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3572. Min Act: -0.0000

Data Index: 470968 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3439. Min Act: -0.0000

Data Index: 873082 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3432. Min Act: -0.0000

Data Index: 1097954 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3426. Min Act: -0.0000

Data Index: 698786 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3518. Min Act: -0.0000

Data Index: 913525 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3621. Min Act: -0.0000

Data Index: 931293 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3597. Min Act: -0.0000

Data Index: 273338 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1304643 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3556. Min Act: -0.0000

Data Index: 960431 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3411. Min Act: -0.0000

Data Index: 222602 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1296148 (C4 (Web Text))

Max Activating Token Index: 50