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

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

Neuron 1542 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.9625. Min Act: -0.0000

Data Index: 272429 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.8377. Min Act: -0.0000

Data Index: 522916 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.8411. Min Act: -0.0000

Data Index: 582706 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.6943. Min Act: -0.0000

Data Index: 323268 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.8285. Min Act: -0.0000

Data Index: 1048737 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.8248. Min Act: -0.0000

Data Index: 295858 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.5685. Min Act: -0.0000

Data Index: 1220681 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.6899. Min Act: -0.0000

Data Index: 1274922 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.6821. Min Act: -0.0000

Data Index: 347120 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.6873. Min Act: -0.0000

Data Index: 117454 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.6803. Min Act: -0.0000

Data Index: 9065 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.6644. Min Act: -0.0000

Data Index: 888971 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.7591. Min Act: -0.0000

Data Index: 960136 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.1703. Min Act: -0.0000

Data Index: 1346844 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.5688. Min Act: -0.0000

Data Index: 1086177 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.4360. Min Act: -0.0000

Data Index: 1067101 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.6858. Min Act: -0.0000

Data Index: 274757 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.5587. Min Act: -0.0000

Data Index: 1005110 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.5517. Min Act: -0.0000

Data Index: 1032778 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 2.9625. Min Range: -2.9625

Max Act: 2.5481. Min Act: -0.0000

Data Index: 88746 (C4 (Web Text))

Max Activating Token Index: 518