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

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

Neuron 3869 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: 0.3047. Min Range: -0.3047

Max Act: 0.3047. Min Act: -0.0003

Data Index: 780825 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2905. Min Act: -0.0003

Data Index: 969175 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2698. Min Act: -0.0003

Data Index: 191498 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2607. Min Act: -0.0003

Data Index: 774223 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2596. Min Act: -0.0003

Data Index: 87778 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2525. Min Act: -0.0002

Data Index: 1324809 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2561. Min Act: -0.0002

Data Index: 1246723 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2442. Min Act: -0.0003

Data Index: 1288553 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2380. Min Act: -0.0003

Data Index: 146746 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2452. Min Act: -0.0002

Data Index: 1010276 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2432. Min Act: -0.0002

Data Index: 923879 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2404. Min Act: -0.0003

Data Index: 653063 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2402. Min Act: -0.0003

Data Index: 559398 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2290. Min Act: -0.0003

Data Index: 298518 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2301. Min Act: -0.0003

Data Index: 225321 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2354. Min Act: -0.0002

Data Index: 1200856 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2347. Min Act: -0.0003

Data Index: 314515 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2244. Min Act: -0.0003

Data Index: 229153 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2246. Min Act: -0.0003

Data Index: 829495 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2321. Min Act: -0.0002

Data Index: 689195 (C4 (Web Text))

Max Activating Token Index: 285