Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 782 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1446. Min Range: -1.1446

Max Act: 1.1177. Min Act: -0.0000

Data Index: 1186659 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 1.1446. Min Range: -1.1446

Max Act: 1.1446. Min Act: -0.0000

Data Index: 602759 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9803. Min Act: -0.0000

Data Index: 582861 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 1.1446. Min Range: -1.1446

Max Act: 1.0219. Min Act: -0.0000

Data Index: 802366 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 1.1446. Min Range: -1.1446

Max Act: 1.0097. Min Act: -0.0000

Data Index: 1348387 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 1.1446. Min Range: -1.1446

Max Act: 1.0049. Min Act: -0.0000

Data Index: 1329381 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1212542 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9462. Min Act: -0.0000

Data Index: 704797 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9700. Min Act: -0.0000

Data Index: 1272056 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9259. Min Act: -0.0000

Data Index: 71968 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8597. Min Act: -0.0000

Data Index: 136451 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.9536. Min Act: -0.0000

Data Index: 872766 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8490. Min Act: -0.0000

Data Index: 677718 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1178812 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.7870. Min Act: -0.0000

Data Index: 888093 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8260. Min Act: -0.0000

Data Index: 389520 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1323817 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8052. Min Act: -0.0000

Data Index: 372152 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8229. Min Act: -0.0000

Data Index: 1071470 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 1.1446. Min Range: -1.1446

Max Act: 0.8540. Min Act: -0.0000

Data Index: 285828 (C4 (Web Text))

Max Activating Token Index: 884