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

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

Neuron 1403 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3199. Min Range: -7.3199

Max Act: 7.3199. Min Act: -0.0002

Data Index: 1643779 (Python Code)

Max Activating Token Index: 593

Text #1

Max Range: 7.3199. Min Range: -7.3199

Max Act: 4.0288. Min Act: -0.0003

Data Index: 1601652 (Python Code)

Max Activating Token Index: 103

Text #2

Max Range: 7.3199. Min Range: -7.3199

Max Act: 2.8878. Min Act: -0.0002

Data Index: 1641948 (Python Code)

Max Activating Token Index: 371

Text #3

Max Range: 7.3199. Min Range: -7.3199

Max Act: 2.6831. Min Act: -0.0003

Data Index: 1652188 (Python Code)

Max Activating Token Index: 450

Text #4

Max Range: 7.3199. Min Range: -7.3199

Max Act: 2.5924. Min Act: -0.0002

Data Index: 1483328 (Python Code)

Max Activating Token Index: 805

Text #5

Max Range: 7.3199. Min Range: -7.3199

Max Act: 2.5265. Min Act: -0.0003

Data Index: 1507671 (Python Code)

Max Activating Token Index: 115

Text #6

Max Range: 7.3199. Min Range: -7.3199

Max Act: 2.4738. Min Act: -0.0002

Data Index: 1423316 (Python Code)

Max Activating Token Index: 61

Text #7

Max Range: 7.3199. Min Range: -7.3199

Max Act: 2.4994. Min Act: -0.0002

Data Index: 1535151 (Python Code)

Max Activating Token Index: 273

Text #8

Max Range: 7.3199. Min Range: -7.3199

Max Act: 2.4389. Min Act: -0.0002

Data Index: 1439139 (Python Code)

Max Activating Token Index: 152

Text #9

Max Range: 7.3199. Min Range: -7.3199

Max Act: 2.3451. Min Act: -0.0003

Data Index: 548783 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 7.3199. Min Range: -7.3199

Max Act: 2.2536. Min Act: -0.0002

Data Index: 1492295 (Python Code)

Max Activating Token Index: 848

Text #11

Max Range: 7.3199. Min Range: -7.3199

Max Act: 2.1880. Min Act: -0.0002

Data Index: 784054 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 7.3199. Min Range: -7.3199

Max Act: 2.1232. Min Act: -0.0002

Data Index: 1529790 (Python Code)

Max Activating Token Index: 717

Text #13

Max Range: 7.3199. Min Range: -7.3199

Max Act: 1.8827. Min Act: -0.0002

Data Index: 1438075 (Python Code)

Max Activating Token Index: 57

Text #14

Max Range: 7.3199. Min Range: -7.3199

Max Act: 1.8889. Min Act: -0.0002

Data Index: 1546413 (Python Code)

Max Activating Token Index: 151

Text #15

Max Range: 7.3199. Min Range: -7.3199

Max Act: 1.8517. Min Act: -0.0002

Data Index: 935352 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 7.3199. Min Range: -7.3199

Max Act: 1.8985. Min Act: -0.0003

Data Index: 1479881 (Python Code)

Max Activating Token Index: 172

Text #17

Max Range: 7.3199. Min Range: -7.3199

Max Act: 1.7079. Min Act: -0.0002

Data Index: 1641169 (Python Code)

Max Activating Token Index: 723

Text #18

Max Range: 7.3199. Min Range: -7.3199

Max Act: 1.7331. Min Act: -0.0003

Data Index: 1562798 (Python Code)

Max Activating Token Index: 324

Text #19

Max Range: 7.3199. Min Range: -7.3199

Max Act: 1.5941. Min Act: -0.0002

Data Index: 1063959 (C4 (Web Text))

Max Activating Token Index: 400