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

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

Neuron 5117 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: 0.2720. Min Range: -0.2720

Max Act: 0.2652. Min Act: -0.0000

Data Index: 424083 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2720. Min Act: -0.0000

Data Index: 168101 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2616. Min Act: -0.0000

Data Index: 219633 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2508. Min Act: -0.0000

Data Index: 131982 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2443. Min Act: -0.0000

Data Index: 1132534 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1179505 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2470. Min Act: -0.0000

Data Index: 767590 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1176422 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2471. Min Act: -0.0000

Data Index: 312807 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2464. Min Act: -0.0000

Data Index: 802996 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1064009 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2440. Min Act: -0.0000

Data Index: 745737 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2247. Min Act: -0.0000

Data Index: 422903 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2243. Min Act: -0.0000

Data Index: 87089 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2399. Min Act: -0.0000

Data Index: 797645 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2303. Min Act: -0.0000

Data Index: 25117 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2370. Min Act: -0.0000

Data Index: 339775 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2354. Min Act: -0.0000

Data Index: 686157 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1271855 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.2720. Min Range: -0.2720

Max Act: 0.2285. Min Act: -0.0000

Data Index: 705099 (C4 (Web Text))

Max Activating Token Index: 999