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

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

Neuron 1475 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: 1.1962. Min Range: -1.1962

Max Act: 1.1863. Min Act: -0.0000

Data Index: 422661 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 1.1962. Min Range: -1.1962

Max Act: 1.1091. Min Act: -0.0000

Data Index: 255408 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 1.1962. Min Range: -1.1962

Max Act: 1.0681. Min Act: -0.0000

Data Index: 134452 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 1.1962. Min Range: -1.1962

Max Act: 1.1962. Min Act: -0.0000

Data Index: 1103496 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 1.1962. Min Range: -1.1962

Max Act: 1.1122. Min Act: -0.0000

Data Index: 183071 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 1.1962. Min Range: -1.1962

Max Act: 1.0941. Min Act: -0.0000

Data Index: 32990 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 1.1962. Min Range: -1.1962

Max Act: 1.0983. Min Act: -0.0000

Data Index: 696551 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 1.1962. Min Range: -1.1962

Max Act: 1.0558. Min Act: -0.0000

Data Index: 468422 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 1.1962. Min Range: -1.1962

Max Act: 1.0299. Min Act: -0.0000

Data Index: 371469 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.9928. Min Act: -0.0000

Data Index: 5458 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 1.1962. Min Range: -1.1962

Max Act: 1.0169. Min Act: -0.0000

Data Index: 1071265 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.9537. Min Act: -0.0000

Data Index: 380099 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.9786. Min Act: -0.0000

Data Index: 423881 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.9799. Min Act: -0.0000

Data Index: 251171 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.9737. Min Act: -0.0000

Data Index: 635584 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.8598. Min Act: -0.0000

Data Index: 215618 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.9652. Min Act: -0.0000

Data Index: 587484 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.9558. Min Act: -0.0000

Data Index: 1131746 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 1.1962. Min Range: -1.1962

Max Act: 0.9544. Min Act: -0.0000

Data Index: 727240 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 1.1962. Min Range: -1.1962

Max Act: 1.0071. Min Act: -0.0000

Data Index: 1141474 (C4 (Web Text))

Max Activating Token Index: 733