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

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

Neuron 761 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1107095 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1280109 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2463. Min Act: -0.0000

Data Index: 643319 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2488. Min Act: -0.0000

Data Index: 1334965 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2481. Min Act: -0.0000

Data Index: 831510 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1101205 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2342. Min Act: -0.0000

Data Index: 494352 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2244. Min Act: -0.0000

Data Index: 800997 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2170. Min Act: -0.0000

Data Index: 714927 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2281. Min Act: -0.0000

Data Index: 801314 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1254201 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2164. Min Act: -0.0000

Data Index: 1077006 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2301. Min Act: -0.0000

Data Index: 663906 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1055326 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.1998. Min Act: -0.0000

Data Index: 498020 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2004. Min Act: -0.0000

Data Index: 249592 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.2007. Min Act: -0.0000

Data Index: 549851 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.1880. Min Act: -0.0000

Data Index: 950932 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.1991. Min Act: -0.0000

Data Index: 1142376 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.2895. Min Range: -0.2895

Max Act: 0.1954. Min Act: -0.0000

Data Index: 814872 (C4 (Web Text))

Max Activating Token Index: 146