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

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

Neuron 4272 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.6220. Min Act: -0.0000

Data Index: 202727 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1088289 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1202691 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.4354. Min Act: -0.0000

Data Index: 1000574 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.3841. Min Act: -0.0000

Data Index: 403091 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.3597. Min Act: -0.0000

Data Index: 238653 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.3427. Min Act: -0.0000

Data Index: 652353 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.3123. Min Act: -0.0000

Data Index: 620393 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.3338. Min Act: -0.0000

Data Index: 287060 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.3051. Min Act: -0.0000

Data Index: 672544 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2846. Min Act: -0.0000

Data Index: 126617 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2944. Min Act: -0.0000

Data Index: 645434 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1196805 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2813. Min Act: -0.0000

Data Index: 350873 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2562. Min Act: -0.0000

Data Index: 1116439 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2687. Min Act: -0.0000

Data Index: 13117 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2306. Min Act: -0.0000

Data Index: 717017 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2553. Min Act: -0.0000

Data Index: 850457 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1053369 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.6220. Min Range: -0.6220

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1318918 (C4 (Web Text))

Max Activating Token Index: 374