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

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

Neuron 2372 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2154. Min Act: -0.0001

Data Index: 731269 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.3914. Min Act: -0.0001

Data Index: 443341 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2406. Min Act: -0.0001

Data Index: 741456 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.3439. Min Act: -0.0001

Data Index: 585624 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.4817. Min Act: -0.0001

Data Index: 973825 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2383. Min Act: -0.0001

Data Index: 1213515 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 3.5444. Min Range: -3.5444

Max Act: 2.9271. Min Act: -0.0001

Data Index: 972584 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.5444. Min Act: -0.0001

Data Index: 1057232 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 3.5444. Min Range: -3.5444

Max Act: 2.9373. Min Act: -0.0001

Data Index: 53467 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.0777. Min Act: -0.0001

Data Index: 473438 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.3359. Min Act: -0.0001

Data Index: 1414621 (Python Code)

Max Activating Token Index: 548

Text #11

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.3410. Min Act: -0.0001

Data Index: 303123 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.3005. Min Act: -0.0001

Data Index: 959214 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.3282. Min Act: -0.0001

Data Index: 1274925 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2240. Min Act: -0.0001

Data Index: 1048036 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.0821. Min Act: -0.0001

Data Index: 767475 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2192. Min Act: -0.0001

Data Index: 842493 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2092. Min Act: -0.0001

Data Index: 1639464 (Python Code)

Max Activating Token Index: 509

Text #18

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.2085. Min Act: -0.0001

Data Index: 1390045 (Python Code)

Max Activating Token Index: 629

Text #19

Max Range: 3.5444. Min Range: -3.5444

Max Act: 3.1624. Min Act: -0.0001

Data Index: 1081929 (C4 (Web Text))

Max Activating Token Index: 414