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

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

Neuron 3338 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.2516. Min Act: -0.0002

Data Index: 546208 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.2195. Min Act: -0.0002

Data Index: 160417 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.0619. Min Act: -0.0002

Data Index: 729650 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.1478. Min Act: -0.0002

Data Index: 27050 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.2343. Min Act: -0.0002

Data Index: 1065733 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.2469. Min Act: -0.0002

Data Index: 753459 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.1575. Min Act: -0.0002

Data Index: 261660 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.1602. Min Act: -0.0002

Data Index: 677882 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.0882. Min Act: -0.0002

Data Index: 249422 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.0228. Min Act: -0.0002

Data Index: 305901 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.1293. Min Act: -0.0002

Data Index: 89837 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.0196. Min Act: -0.0002

Data Index: 1196403 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.0284. Min Act: -0.0002

Data Index: 180846 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.2516. Min Range: -1.2516

Max Act: 0.9705. Min Act: -0.0002

Data Index: 736384 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 1.2516. Min Range: -1.2516

Max Act: 0.9040. Min Act: -0.0002

Data Index: 947204 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.0120. Min Act: -0.0002

Data Index: 889412 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 1.2516. Min Range: -1.2516

Max Act: 0.9457. Min Act: -0.0002

Data Index: 312058 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 1.2516. Min Range: -1.2516

Max Act: 0.9961. Min Act: -0.0002

Data Index: 518025 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 1.2516. Min Range: -1.2516

Max Act: 1.1336. Min Act: -0.0002

Data Index: 458185 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 1.2516. Min Range: -1.2516

Max Act: 0.9514. Min Act: -0.0002

Data Index: 47156 (C4 (Web Text))

Max Activating Token Index: 205