Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3402 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1820. Min Range: -1.1820

Max Act: 1.1798. Min Act: -0.0001

Data Index: 533006 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 1.1820. Min Range: -1.1820

Max Act: 1.1820. Min Act: -0.0001

Data Index: 1196138 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 1.1820. Min Range: -1.1820

Max Act: 1.0449. Min Act: -0.0001

Data Index: 1050222 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 1.1820. Min Range: -1.1820

Max Act: 1.1428. Min Act: -0.0001

Data Index: 837013 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.8882. Min Act: -0.0001

Data Index: 964535 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 1.1820. Min Range: -1.1820

Max Act: 1.0244. Min Act: -0.0001

Data Index: 155366 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 1.1820. Min Range: -1.1820

Max Act: 1.0435. Min Act: -0.0001

Data Index: 1225039 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 1.1820. Min Range: -1.1820

Max Act: 1.0138. Min Act: -0.0001

Data Index: 1063823 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 1.1820. Min Range: -1.1820

Max Act: 1.0028. Min Act: -0.0001

Data Index: 161635 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.8968. Min Act: -0.0001

Data Index: 516445 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.9753. Min Act: -0.0001

Data Index: 672459 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.9537. Min Act: -0.0001

Data Index: 242289 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.9517. Min Act: -0.0001

Data Index: 328170 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.9472. Min Act: -0.0001

Data Index: 1228422 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 1.1820. Min Range: -1.1820

Max Act: 1.0435. Min Act: -0.0001

Data Index: 766291 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.9687. Min Act: -0.0001

Data Index: 239353 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.9639. Min Act: -0.0001

Data Index: 192098 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 1.1820. Min Range: -1.1820

Max Act: 1.0254. Min Act: -0.0001

Data Index: 328083 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.9495. Min Act: -0.0001

Data Index: 36559 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 1.1820. Min Range: -1.1820

Max Act: 1.0102. Min Act: -0.0001

Data Index: 457488 (C4 (Web Text))

Max Activating Token Index: 980