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

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

Neuron 1081 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3534. Min Range: -4.3534

Max Act: 4.3534. Min Act: -0.0000

Data Index: 346156 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 4.3534. Min Range: -4.3534

Max Act: 4.2691. Min Act: -0.0000

Data Index: 463900 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.4196. Min Act: -0.0000

Data Index: 131382 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.9713. Min Act: -0.0000

Data Index: 1186722 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.5595. Min Act: -0.0000

Data Index: 267469 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.8755. Min Act: -0.0000

Data Index: 388171 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.5040. Min Act: -0.0000

Data Index: 368777 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.6582. Min Act: -0.0000

Data Index: 1031388 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.7616. Min Act: -0.0000

Data Index: 1118264 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.5786. Min Act: -0.0000

Data Index: 869517 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.5417. Min Act: -0.0000

Data Index: 670580 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.4350. Min Act: -0.0000

Data Index: 1172115 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.4155. Min Act: -0.0000

Data Index: 1354501 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.4033. Min Act: -0.0000

Data Index: 1240990 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.4130. Min Act: -0.0000

Data Index: 240191 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.3592. Min Act: -0.0000

Data Index: 1226653 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.0508. Min Act: -0.0000

Data Index: 524523 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.1646. Min Act: -0.0000

Data Index: 247194 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.1578. Min Act: -0.0000

Data Index: 393429 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 4.3534. Min Range: -4.3534

Max Act: 3.1212. Min Act: -0.0000

Data Index: 423645 (C4 (Web Text))

Max Activating Token Index: 52