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

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

Neuron 2462 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: 2.0665. Min Range: -2.0665

Max Act: 2.0665. Min Act: -0.0000

Data Index: 1149082 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 2.0665. Min Range: -2.0665

Max Act: 1.5119. Min Act: -0.0000

Data Index: 1089341 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 2.0665. Min Range: -2.0665

Max Act: 1.5926. Min Act: -0.0000

Data Index: 73450 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 2.0665. Min Range: -2.0665

Max Act: 1.3010. Min Act: -0.0000

Data Index: 905431 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 2.0665. Min Range: -2.0665

Max Act: 1.3660. Min Act: -0.0000

Data Index: 268980 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 2.0665. Min Range: -2.0665

Max Act: 1.2114. Min Act: 0.0000

Data Index: 482218 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 2.0665. Min Range: -2.0665

Max Act: 1.1477. Min Act: -0.0000

Data Index: 677289 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 2.0665. Min Range: -2.0665

Max Act: 1.0040. Min Act: -0.0000

Data Index: 351756 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 2.0665. Min Range: -2.0665

Max Act: 1.0548. Min Act: -0.0000

Data Index: 94222 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 2.0665. Min Range: -2.0665

Max Act: 1.0415. Min Act: -0.0000

Data Index: 464110 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 2.0665. Min Range: -2.0665

Max Act: 0.9598. Min Act: -0.0000

Data Index: 457564 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 2.0665. Min Range: -2.0665

Max Act: 1.0101. Min Act: -0.0000

Data Index: 94031 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 2.0665. Min Range: -2.0665

Max Act: 1.0027. Min Act: -0.0000

Data Index: 1349619 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 2.0665. Min Range: -2.0665

Max Act: 1.0495. Min Act: -0.0000

Data Index: 26620 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 2.0665. Min Range: -2.0665

Max Act: 1.0462. Min Act: -0.0000

Data Index: 699483 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 2.0665. Min Range: -2.0665

Max Act: 1.0441. Min Act: -0.0000

Data Index: 84042 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 2.0665. Min Range: -2.0665

Max Act: 0.9662. Min Act: -0.0000

Data Index: 1038592 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 2.0665. Min Range: -2.0665

Max Act: 0.9500. Min Act: 0.0000

Data Index: 521957 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 2.0665. Min Range: -2.0665

Max Act: 0.9554. Min Act: -0.0000

Data Index: 721977 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 2.0665. Min Range: -2.0665

Max Act: 0.9310. Min Act: -0.0000

Data Index: 239028 (C4 (Web Text))

Max Activating Token Index: 357