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

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

Neuron 5102 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: 1.3667. Min Range: -1.3667

Max Act: 1.3667. Min Act: -0.0000

Data Index: 420096 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2139. Min Act: -0.0000

Data Index: 632976 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2705. Min Act: -0.0000

Data Index: 187230 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2297. Min Act: -0.0000

Data Index: 1116112 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.1688. Min Act: -0.0000

Data Index: 1291754 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0751. Min Act: -0.0000

Data Index: 857004 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0023. Min Act: -0.0000

Data Index: 792839 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0974. Min Act: -0.0000

Data Index: 43214 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0478. Min Act: -0.0000

Data Index: 423586 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0411. Min Act: -0.0000

Data Index: 24465 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0079. Min Act: -0.0000

Data Index: 782915 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9770. Min Act: -0.0000

Data Index: 119931 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0301. Min Act: -0.0000

Data Index: 713238 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9990. Min Act: -0.0000

Data Index: 821195 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0015. Min Act: -0.0000

Data Index: 1148414 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9975. Min Act: -0.0000

Data Index: 680525 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0547. Min Act: -0.0000

Data Index: 1067048 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0170. Min Act: -0.0000

Data Index: 1347233 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0291. Min Act: -0.0000

Data Index: 40708 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9903. Min Act: -0.0000

Data Index: 1208111 (C4 (Web Text))

Max Activating Token Index: 386