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

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

Neuron 50 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: 1.2410. Min Range: -1.2410

Max Act: 1.2410. Min Act: -0.0001

Data Index: 1076941 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1116. Min Act: -0.0002

Data Index: 212069 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1475. Min Act: -0.0001

Data Index: 255614 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1584. Min Act: -0.0002

Data Index: 946298 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0528. Min Act: -0.0001

Data Index: 516230 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1699. Min Act: -0.0002

Data Index: 710484 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0701. Min Act: -0.0001

Data Index: 1187733 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0527. Min Act: -0.0001

Data Index: 803960 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1117. Min Act: -0.0001

Data Index: 465381 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0708. Min Act: -0.0001

Data Index: 479425 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0625. Min Act: -0.0002

Data Index: 1042290 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0341. Min Act: -0.0002

Data Index: 292943 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1607. Min Act: -0.0001

Data Index: 512988 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0255. Min Act: -0.0001

Data Index: 509822 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0102. Min Act: -0.0002

Data Index: 1052956 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.9218. Min Act: -0.0001

Data Index: 1086170 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0701. Min Act: -0.0002

Data Index: 8103 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0028. Min Act: -0.0001

Data Index: 165387 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0625. Min Act: -0.0001

Data Index: 1318079 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.9558. Min Act: -0.0002

Data Index: 807933 (C4 (Web Text))

Max Activating Token Index: 1020