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

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

Neuron 667 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2524. Min Act: -0.0000

Data Index: 538449 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2250. Min Act: -0.0000

Data Index: 1282879 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2201. Min Act: -0.0000

Data Index: 100630 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2244. Min Act: -0.0000

Data Index: 999208 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2197. Min Act: -0.0000

Data Index: 89640 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1056005 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2119. Min Act: -0.0000

Data Index: 84180 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2097. Min Act: -0.0001

Data Index: 1105131 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2065. Min Act: -0.0001

Data Index: 793495 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1108636 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2034. Min Act: -0.0000

Data Index: 791904 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2018. Min Act: -0.0000

Data Index: 532821 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2047. Min Act: -0.0000

Data Index: 3105 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2031. Min Act: -0.0000

Data Index: 737656 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1181449 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1962. Min Act: -0.0000

Data Index: 394042 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1902. Min Act: -0.0000

Data Index: 522743 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1814. Min Act: 0.0000

Data Index: 1062123 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1925. Min Act: -0.0001

Data Index: 78877 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.2524. Min Range: -0.2524

Max Act: 0.1859. Min Act: -0.0001

Data Index: 42421 (C4 (Web Text))

Max Activating Token Index: 40