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

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

Neuron 2612 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.5911. Min Act: -0.0000

Data Index: 193181 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.3219. Min Act: -0.0000

Data Index: 795072 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.2596. Min Act: -0.0000

Data Index: 1175212 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.2803. Min Act: -0.0000

Data Index: 870847 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.2654. Min Act: -0.0000

Data Index: 105995 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.2445. Min Act: -0.0000

Data Index: 586115 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.2291. Min Act: -0.0000

Data Index: 1229964 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.1595. Min Act: -0.0000

Data Index: 333528 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.1488. Min Act: -0.0000

Data Index: 168716 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.0718. Min Act: -0.0000

Data Index: 639644 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.1799. Min Act: -0.0000

Data Index: 1016125 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.0434. Min Act: -0.0000

Data Index: 1133022 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.0476. Min Act: -0.0000

Data Index: 250145 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.0358. Min Act: -0.0000

Data Index: 746483 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.0097. Min Act: -0.0000

Data Index: 152188 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.0644. Min Act: -0.0000

Data Index: 694865 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.0623. Min Act: -0.0000

Data Index: 494974 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.0662. Min Act: -0.0000

Data Index: 829305 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.1129. Min Act: -0.0000

Data Index: 546457 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 1.5911. Min Range: -1.5911

Max Act: 1.0032. Min Act: -0.0000

Data Index: 237207 (C4 (Web Text))

Max Activating Token Index: 369