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

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

Neuron 107 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: 0.0816. Min Range: -0.0816

Max Act: 0.0816. Min Act: -0.0002

Data Index: 694935 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1281206 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1151207 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0605. Min Act: -0.0002

Data Index: 515193 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0578. Min Act: -0.0002

Data Index: 911556 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1212641 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0604. Min Act: -0.0002

Data Index: 960906 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0605. Min Act: -0.0002

Data Index: 603598 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0595. Min Act: -0.0002

Data Index: 487984 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1320183 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1210329 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0579. Min Act: -0.0002

Data Index: 300269 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0567. Min Act: -0.0002

Data Index: 29599 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0579. Min Act: -0.0002

Data Index: 748895 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0575. Min Act: -0.0002

Data Index: 267779 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0574. Min Act: -0.0002

Data Index: 833514 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1152343 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0560. Min Act: -0.0002

Data Index: 890611 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1003416 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 0.0816. Min Range: -0.0816

Max Act: 0.0536. Min Act: -0.0002

Data Index: 642775 (C4 (Web Text))

Max Activating Token Index: 164