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

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

Neuron 4488 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.8645. Min Act: -0.0000

Data Index: 959224 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.5161. Min Act: -0.0000

Data Index: 1267140 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.4556. Min Act: -0.0000

Data Index: 796209 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.3967. Min Act: -0.0000

Data Index: 560446 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.3935. Min Act: -0.0000

Data Index: 721737 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.3412. Min Act: -0.0000

Data Index: 264046 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.4401. Min Act: -0.0000

Data Index: 1044504 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.4481. Min Act: -0.0000

Data Index: 170923 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.2561. Min Act: -0.0000

Data Index: 754781 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.2531. Min Act: -0.0000

Data Index: 96011 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.2406. Min Act: -0.0000

Data Index: 322140 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.2343. Min Act: -0.0000

Data Index: 789749 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.3014. Min Act: -0.0000

Data Index: 153449 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.1595. Min Act: -0.0000

Data Index: 376107 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.0388. Min Act: -0.0000

Data Index: 1180932 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.0313. Min Act: -0.0000

Data Index: 954037 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.1279. Min Act: -0.0000

Data Index: 1350778 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.1174. Min Act: -0.0000

Data Index: 1292369 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 2.8645. Min Range: -2.8645

Max Act: 1.9881. Min Act: -0.0000

Data Index: 1009281 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 2.8645. Min Range: -2.8645

Max Act: 2.2278. Min Act: -0.0000

Data Index: 1052110 (C4 (Web Text))

Max Activating Token Index: 697