Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1635 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.9350. Min Act: -0.0002

Data Index: 916390 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.8810. Min Act: -0.0002

Data Index: 787304 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.8488. Min Act: -0.0001

Data Index: 543696 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.8225. Min Act: -0.0001

Data Index: 273658 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.7592. Min Act: -0.0001

Data Index: 396953 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.8309. Min Act: -0.0001

Data Index: 902857 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.8193. Min Act: -0.0002

Data Index: 517872 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.7737. Min Act: -0.0002

Data Index: 124664 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.8282. Min Act: -0.0002

Data Index: 812819 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.7739. Min Act: -0.0001

Data Index: 572912 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.7432. Min Act: -0.0002

Data Index: 1192258 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.7103. Min Act: -0.0002

Data Index: 696368 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.7111. Min Act: -0.0002

Data Index: 380999 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.7795. Min Act: -0.0002

Data Index: 307132 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.7477. Min Act: -0.0002

Data Index: 612781 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.7490. Min Act: -0.0001

Data Index: 300035 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.7226. Min Act: -0.0001

Data Index: 17987 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.6791. Min Act: -0.0002

Data Index: 579132 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.6984. Min Act: -0.0002

Data Index: 708051 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.9350. Min Range: -0.9350

Max Act: 0.7357. Min Act: -0.0001

Data Index: 778173 (C4 (Web Text))

Max Activating Token Index: 615