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

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

Neuron 639 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: 2.4661. Min Range: -2.4661

Max Act: 2.4661. Min Act: -0.0000

Data Index: 89073 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.8953. Min Act: -0.0000

Data Index: 106560 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.7139. Min Act: -0.0000

Data Index: 1252866 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.6756. Min Act: -0.0000

Data Index: 429807 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.5055. Min Act: -0.0000

Data Index: 106762 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.4904. Min Act: -0.0000

Data Index: 1304099 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.4650. Min Act: -0.0000

Data Index: 997798 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.3785. Min Act: -0.0000

Data Index: 1068805 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.3745. Min Act: -0.0000

Data Index: 362694 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.3301. Min Act: -0.0000

Data Index: 1068692 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.4083. Min Act: -0.0000

Data Index: 1351660 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.3336. Min Act: -0.0000

Data Index: 215272 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.3031. Min Act: -0.0000

Data Index: 1334408 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.3804. Min Act: -0.0000

Data Index: 1306100 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.3238. Min Act: -0.0000

Data Index: 452170 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.2098. Min Act: -0.0000

Data Index: 1016231 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.2776. Min Act: -0.0000

Data Index: 136437 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.3565. Min Act: -0.0000

Data Index: 336552 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.2728. Min Act: -0.0000

Data Index: 1213168 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 2.4661. Min Range: -2.4661

Max Act: 1.2211. Min Act: -0.0000

Data Index: 94521 (C4 (Web Text))

Max Activating Token Index: 353