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

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

Neuron 3750 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.8436. Min Act: -0.0000

Data Index: 839405 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.6976. Min Act: -0.0000

Data Index: 181564 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.6230. Min Act: -0.0000

Data Index: 262538 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5833. Min Act: -0.0000

Data Index: 170077 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5915. Min Act: -0.0000

Data Index: 185783 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.6217. Min Act: -0.0000

Data Index: 461821 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.6298. Min Act: -0.0000

Data Index: 82740 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5970. Min Act: -0.0000

Data Index: 208277 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.6046. Min Act: -0.0000

Data Index: 306289 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5817. Min Act: -0.0000

Data Index: 382463 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5859. Min Act: -0.0000

Data Index: 371511 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5706. Min Act: -0.0000

Data Index: 405209 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5640. Min Act: -0.0000

Data Index: 1120665 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5889. Min Act: -0.0000

Data Index: 1216600 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5482. Min Act: -0.0000

Data Index: 37783 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1165725 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5330. Min Act: -0.0000

Data Index: 907527 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5189. Min Act: -0.0000

Data Index: 414138 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5342. Min Act: -0.0000

Data Index: 395531 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 0.8436. Min Range: -0.8436

Max Act: 0.5251. Min Act: -0.0000

Data Index: 492051 (C4 (Web Text))

Max Activating Token Index: 728