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

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

Neuron 3794 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: 2.9519. Min Range: -2.9519

Max Act: 2.9519. Min Act: -0.0000

Data Index: 1045273 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 2.9519. Min Range: -2.9519

Max Act: 2.5725. Min Act: -0.0000

Data Index: 916386 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 2.9519. Min Range: -2.9519

Max Act: 2.3516. Min Act: -0.0000

Data Index: 1083944 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 2.9519. Min Range: -2.9519

Max Act: 2.4596. Min Act: -0.0000

Data Index: 394783 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 2.9519. Min Range: -2.9519

Max Act: 2.3150. Min Act: -0.0000

Data Index: 1146944 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 2.9519. Min Range: -2.9519

Max Act: 2.2609. Min Act: -0.0000

Data Index: 140453 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 2.9519. Min Range: -2.9519

Max Act: 2.1020. Min Act: -0.0000

Data Index: 995723 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 2.9519. Min Range: -2.9519

Max Act: 2.2138. Min Act: -0.0000

Data Index: 1207665 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 2.9519. Min Range: -2.9519

Max Act: 2.1881. Min Act: -0.0000

Data Index: 981297 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 2.9519. Min Range: -2.9519

Max Act: 2.0620. Min Act: -0.0000

Data Index: 233808 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 2.9519. Min Range: -2.9519

Max Act: 2.3989. Min Act: -0.0000

Data Index: 553696 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 2.9519. Min Range: -2.9519

Max Act: 2.2477. Min Act: -0.0000

Data Index: 1233219 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 2.9519. Min Range: -2.9519

Max Act: 2.3656. Min Act: -0.0000

Data Index: 1098264 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 2.9519. Min Range: -2.9519

Max Act: 2.1411. Min Act: -0.0000

Data Index: 278260 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 2.9519. Min Range: -2.9519

Max Act: 2.1358. Min Act: -0.0000

Data Index: 319303 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 2.9519. Min Range: -2.9519

Max Act: 2.0836. Min Act: -0.0000

Data Index: 1250667 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 2.9519. Min Range: -2.9519

Max Act: 1.9958. Min Act: -0.0000

Data Index: 1317264 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 2.9519. Min Range: -2.9519

Max Act: 2.1989. Min Act: -0.0000

Data Index: 801451 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 2.9519. Min Range: -2.9519

Max Act: 2.0737. Min Act: -0.0000

Data Index: 681507 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 2.9519. Min Range: -2.9519

Max Act: 1.9350. Min Act: -0.0000

Data Index: 56355 (C4 (Web Text))

Max Activating Token Index: 345