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

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

Neuron 4597 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0351. Min Range: -1.0351

Max Act: 1.0351. Min Act: -0.0000

Data Index: 318249 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8856. Min Act: -0.0000

Data Index: 877889 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8979. Min Act: -0.0000

Data Index: 170792 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8242. Min Act: -0.0000

Data Index: 964155 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8831. Min Act: -0.0000

Data Index: 116738 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7791. Min Act: -0.0000

Data Index: 727691 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7732. Min Act: -0.0000

Data Index: 903800 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1007866 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7101. Min Act: -0.0000

Data Index: 425345 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7662. Min Act: -0.0000

Data Index: 1275644 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7305. Min Act: -0.0000

Data Index: 748614 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7499. Min Act: -0.0000

Data Index: 629630 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7168. Min Act: -0.0000

Data Index: 431281 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7309. Min Act: -0.0000

Data Index: 545016 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7152. Min Act: -0.0000

Data Index: 459461 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7251. Min Act: -0.0000

Data Index: 1311669 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7223. Min Act: -0.0000

Data Index: 927316 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.6852. Min Act: -0.0000

Data Index: 672827 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.6705. Min Act: -0.0000

Data Index: 295727 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.6456. Min Act: -0.0000

Data Index: 946597 (C4 (Web Text))

Max Activating Token Index: 173