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

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

Neuron 3751 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3566. Min Range: -4.3566

Max Act: 4.3566. Min Act: -0.0000

Data Index: 996009 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.8209. Min Act: -0.0000

Data Index: 1073064 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.7824. Min Act: -0.0000

Data Index: 500374 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.5275. Min Act: -0.0000

Data Index: 571088 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.5479. Min Act: -0.0000

Data Index: 1323811 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.5520. Min Act: -0.0000

Data Index: 16470 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.7495. Min Act: -0.0000

Data Index: 1012906 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.5867. Min Act: -0.0000

Data Index: 667796 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.4053. Min Act: -0.0000

Data Index: 507970 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.2179. Min Act: -0.0000

Data Index: 102392 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.3740. Min Act: -0.0000

Data Index: 663632 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.5169. Min Act: -0.0000

Data Index: 609540 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.2044. Min Act: -0.0000

Data Index: 116607 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.1098. Min Act: -0.0000

Data Index: 365020 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.2581. Min Act: -0.0000

Data Index: 186356 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.1993. Min Act: -0.0000

Data Index: 39585 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.3236. Min Act: -0.0000

Data Index: 1050850 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.1597. Min Act: -0.0000

Data Index: 660952 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.2968. Min Act: -0.0000

Data Index: 934627 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 4.3566. Min Range: -4.3566

Max Act: 3.1313. Min Act: -0.0000

Data Index: 939375 (C4 (Web Text))

Max Activating Token Index: 665