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

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

Neuron 642 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.5149. Min Act: -0.0000

Data Index: 932536 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.4730. Min Act: -0.0000

Data Index: 147323 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.5479. Min Act: -0.0000

Data Index: 950709 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.5281. Min Act: -0.0000

Data Index: 489978 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.2930. Min Act: -0.0000

Data Index: 1137262 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.2726. Min Act: -0.0000

Data Index: 1290182 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.2024. Min Act: -0.0000

Data Index: 1098350 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.0544. Min Act: -0.0000

Data Index: 808027 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.0907. Min Act: -0.0000

Data Index: 778478 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.0279. Min Act: -0.0000

Data Index: 811406 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.1490. Min Act: -0.0000

Data Index: 734768 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.0812. Min Act: -0.0000

Data Index: 533517 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.1164. Min Act: -0.0000

Data Index: 1005694 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.0545. Min Act: -0.0000

Data Index: 1356431 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1040541 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.0262. Min Act: -0.0000

Data Index: 1538125 (Python Code)

Max Activating Token Index: 832

Text #16

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.0260. Min Act: -0.0000

Data Index: 1153248 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.0052. Min Act: -0.0000

Data Index: 818117 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.0224. Min Act: -0.0000

Data Index: 1268363 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.0135. Min Act: -0.0000

Data Index: 77136 (C4 (Web Text))

Max Activating Token Index: 930