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

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

Neuron 284 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: 0.0796. Min Range: -0.0796

Max Act: 0.0796. Min Act: -0.0002

Data Index: 710135 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0745. Min Act: -0.0002

Data Index: 70345 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0702. Min Act: -0.0002

Data Index: 813369 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0691. Min Act: -0.0002

Data Index: 71470 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0652. Min Act: -0.0002

Data Index: 337026 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0598. Min Act: -0.0002

Data Index: 482541 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0634. Min Act: -0.0002

Data Index: 709994 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0632. Min Act: -0.0002

Data Index: 895204 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0632. Min Act: -0.0002

Data Index: 705245 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0629. Min Act: -0.0002

Data Index: 332309 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0624. Min Act: -0.0002

Data Index: 525931 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1111110 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1033220 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0600. Min Act: -0.0002

Data Index: 647240 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0607. Min Act: -0.0002

Data Index: 91568 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0584. Min Act: -0.0002

Data Index: 24924 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0598. Min Act: -0.0002

Data Index: 49711 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1260647 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1103494 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0598. Min Act: -0.0002

Data Index: 973720 (C4 (Web Text))

Max Activating Token Index: 598