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

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

Neuron 4386 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2308. Min Range: -1.2308

Max Act: 1.2308. Min Act: -0.0000

Data Index: 854750 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 1.2308. Min Range: -1.2308

Max Act: 1.0857. Min Act: -0.0000

Data Index: 445852 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 1.2308. Min Range: -1.2308

Max Act: 1.1291. Min Act: -0.0000

Data Index: 1240846 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 1.2308. Min Range: -1.2308

Max Act: 1.1774. Min Act: -0.0000

Data Index: 107284 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 1.2308. Min Range: -1.2308

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1143849 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 1.2308. Min Range: -1.2308

Max Act: 0.8176. Min Act: -0.0000

Data Index: 828343 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 1.2308. Min Range: -1.2308

Max Act: 0.8411. Min Act: -0.0000

Data Index: 1304457 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 1.2308. Min Range: -1.2308

Max Act: 0.9006. Min Act: -0.0000

Data Index: 117580 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 1.2308. Min Range: -1.2308

Max Act: 0.7995. Min Act: -0.0000

Data Index: 632801 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 1.2308. Min Range: -1.2308

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1061913 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 1.2308. Min Range: -1.2308

Max Act: 0.7819. Min Act: -0.0000

Data Index: 362709 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 1.2308. Min Range: -1.2308

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1156220 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 1.2308. Min Range: -1.2308

Max Act: 0.7254. Min Act: -0.0000

Data Index: 21020 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 1.2308. Min Range: -1.2308

Max Act: 0.7374. Min Act: -0.0000

Data Index: 490351 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 1.2308. Min Range: -1.2308

Max Act: 0.6868. Min Act: -0.0000

Data Index: 777661 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 1.2308. Min Range: -1.2308

Max Act: 0.7753. Min Act: -0.0000

Data Index: 961626 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 1.2308. Min Range: -1.2308

Max Act: 0.6728. Min Act: -0.0000

Data Index: 66633 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 1.2308. Min Range: -1.2308

Max Act: 0.6452. Min Act: -0.0000

Data Index: 155042 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 1.2308. Min Range: -1.2308

Max Act: 0.5797. Min Act: -0.0000

Data Index: 321887 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 1.2308. Min Range: -1.2308

Max Act: 0.6374. Min Act: -0.0000

Data Index: 500799 (C4 (Web Text))

Max Activating Token Index: 432