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

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

Neuron 1944 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: 2.8278. Min Range: -2.8278

Max Act: 2.8278. Min Act: -0.0000

Data Index: 1419135 (Python Code)

Max Activating Token Index: 176

Text #1

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.7340. Min Act: -0.0000

Data Index: 1422820 (Python Code)

Max Activating Token Index: 86

Text #2

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.4168. Min Act: -0.0000

Data Index: 1602316 (Python Code)

Max Activating Token Index: 939

Text #3

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.5436. Min Act: -0.0000

Data Index: 1574708 (Python Code)

Max Activating Token Index: 597

Text #4

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.2708. Min Act: -0.0000

Data Index: 1625297 (Python Code)

Max Activating Token Index: 687

Text #5

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.3956. Min Act: -0.0001

Data Index: 1544146 (Python Code)

Max Activating Token Index: 89

Text #6

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.3287. Min Act: -0.0000

Data Index: 1561097 (Python Code)

Max Activating Token Index: 133

Text #7

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.2291. Min Act: -0.0000

Data Index: 1587189 (Python Code)

Max Activating Token Index: 903

Text #8

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.1394. Min Act: -0.0000

Data Index: 1640565 (Python Code)

Max Activating Token Index: 982

Text #9

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.2083. Min Act: -0.0000

Data Index: 1556392 (Python Code)

Max Activating Token Index: 818

Text #10

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.1563. Min Act: -0.0000

Data Index: 1498286 (Python Code)

Max Activating Token Index: 183

Text #11

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.0966. Min Act: -0.0000

Data Index: 1484688 (Python Code)

Max Activating Token Index: 44

Text #12

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.2016. Min Act: -0.0000

Data Index: 1455366 (Python Code)

Max Activating Token Index: 126

Text #13

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.2030. Min Act: -0.0000

Data Index: 1452192 (Python Code)

Max Activating Token Index: 204

Text #14

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.1888. Min Act: -0.0000

Data Index: 1497318 (Python Code)

Max Activating Token Index: 548

Text #15

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.2200. Min Act: -0.0000

Data Index: 1371349 (Python Code)

Max Activating Token Index: 292

Text #16

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.0896. Min Act: -0.0000

Data Index: 1605794 (Python Code)

Max Activating Token Index: 670

Text #17

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.0811. Min Act: -0.0000

Data Index: 1443008 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 2.8278. Min Range: -2.8278

Max Act: 2.1192. Min Act: -0.0000

Data Index: 1555625 (Python Code)

Max Activating Token Index: 109

Text #19

Max Range: 2.8278. Min Range: -2.8278

Max Act: 1.9580. Min Act: -0.0000

Data Index: 1544905 (Python Code)

Max Activating Token Index: 945