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

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

Neuron 4860 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1006. Min Range: -2.1006

Max Act: 2.1006. Min Act: -0.0000

Data Index: 831833 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.4136. Min Act: -0.0000

Data Index: 563728 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.1968. Min Act: -0.0001

Data Index: 339437 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.2441. Min Act: -0.0001

Data Index: 500731 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.1348. Min Act: -0.0001

Data Index: 702268 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.1323. Min Act: -0.0001

Data Index: 105644 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.0953. Min Act: -0.0001

Data Index: 967390 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.2207. Min Act: -0.0001

Data Index: 203148 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.1746. Min Act: -0.0001

Data Index: 337060 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.2359. Min Act: -0.0000

Data Index: 1128633 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.2258. Min Act: -0.0001

Data Index: 285618 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.1252. Min Act: -0.0001

Data Index: 27996 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.1751. Min Act: -0.0000

Data Index: 47637 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.1052. Min Act: -0.0001

Data Index: 217835 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.0931. Min Act: -0.0001

Data Index: 966047 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.1008. Min Act: -0.0000

Data Index: 1309473 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 2.1006. Min Range: -2.1006

Max Act: 0.9812. Min Act: -0.0001

Data Index: 390506 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.0830. Min Act: -0.0001

Data Index: 724681 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.0851. Min Act: -0.0001

Data Index: 658307 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 2.1006. Min Range: -2.1006

Max Act: 1.0026. Min Act: -0.0000

Data Index: 25156 (C4 (Web Text))

Max Activating Token Index: 393