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

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

Neuron 510 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: 2.1575. Min Range: -2.1575

Max Act: 2.1575. Min Act: -0.0000

Data Index: 75836 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 2.1575. Min Range: -2.1575

Max Act: 1.8140. Min Act: -0.0000

Data Index: 1033878 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 2.1575. Min Range: -2.1575

Max Act: 1.5195. Min Act: -0.0000

Data Index: 1140052 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 2.1575. Min Range: -2.1575

Max Act: 1.2310. Min Act: -0.0000

Data Index: 316109 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 2.1575. Min Range: -2.1575

Max Act: 1.1989. Min Act: -0.0000

Data Index: 1335810 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 2.1575. Min Range: -2.1575

Max Act: 1.1766. Min Act: -0.0000

Data Index: 208482 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 2.1575. Min Range: -2.1575

Max Act: 1.2013. Min Act: -0.0000

Data Index: 883913 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 2.1575. Min Range: -2.1575

Max Act: 1.0647. Min Act: -0.0000

Data Index: 1292528 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 2.1575. Min Range: -2.1575

Max Act: 1.0123. Min Act: -0.0000

Data Index: 238655 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 2.1575. Min Range: -2.1575

Max Act: 1.0337. Min Act: -0.0000

Data Index: 779037 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 2.1575. Min Range: -2.1575

Max Act: 1.0354. Min Act: -0.0000

Data Index: 681734 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 2.1575. Min Range: -2.1575

Max Act: 0.9616. Min Act: -0.0000

Data Index: 733379 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 2.1575. Min Range: -2.1575

Max Act: 0.9648. Min Act: -0.0000

Data Index: 809084 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 2.1575. Min Range: -2.1575

Max Act: 0.9358. Min Act: -0.0000

Data Index: 145466 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 2.1575. Min Range: -2.1575

Max Act: 0.9363. Min Act: -0.0000

Data Index: 379739 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 2.1575. Min Range: -2.1575

Max Act: 0.9928. Min Act: -0.0000

Data Index: 946539 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 2.1575. Min Range: -2.1575

Max Act: 0.9361. Min Act: -0.0000

Data Index: 753708 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 2.1575. Min Range: -2.1575

Max Act: 0.9597. Min Act: -0.0000

Data Index: 50551 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 2.1575. Min Range: -2.1575

Max Act: 0.9497. Min Act: -0.0000

Data Index: 358472 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 2.1575. Min Range: -2.1575

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1265421 (C4 (Web Text))

Max Activating Token Index: 331