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

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

Neuron 318 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4855. Min Act: -0.0000

Data Index: 669235 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.5608. Min Act: -0.0000

Data Index: 664208 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4873. Min Act: -0.0000

Data Index: 71616 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.5015. Min Act: -0.0000

Data Index: 271440 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.5146. Min Act: -0.0000

Data Index: 126119 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4911. Min Act: -0.0000

Data Index: 276406 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4889. Min Act: -0.0000

Data Index: 685449 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4513. Min Act: -0.0000

Data Index: 107649 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1069731 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4241. Min Act: -0.0000

Data Index: 981060 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4556. Min Act: -0.0000

Data Index: 247252 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4835. Min Act: -0.0000

Data Index: 1232989 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1259434 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4416. Min Act: -0.0000

Data Index: 804756 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4359. Min Act: -0.0000

Data Index: 847184 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4166. Min Act: -0.0000

Data Index: 381384 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4442. Min Act: -0.0000

Data Index: 124768 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4313. Min Act: -0.0000

Data Index: 1216681 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.3712. Min Act: -0.0000

Data Index: 264421 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4430. Min Act: -0.0000

Data Index: 405404 (C4 (Web Text))

Max Activating Token Index: 98