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

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

Neuron 711 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.6737. Min Act: -0.0000

Data Index: 341401 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.3859. Min Act: -0.0000

Data Index: 161421 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.3842. Min Act: -0.0000

Data Index: 496086 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.3568. Min Act: -0.0000

Data Index: 758918 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.3563. Min Act: -0.0000

Data Index: 723656 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.3410. Min Act: -0.0001

Data Index: 325790 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.2335. Min Act: -0.0001

Data Index: 64869 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.2305. Min Act: -0.0001

Data Index: 268637 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.2302. Min Act: -0.0001

Data Index: 378983 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.2338. Min Act: -0.0001

Data Index: 603906 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.2354. Min Act: -0.0000

Data Index: 462932 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1071121 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.2282. Min Act: -0.0000

Data Index: 405055 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.2233. Min Act: -0.0000

Data Index: 820557 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.2292. Min Act: -0.0000

Data Index: 500509 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.2204. Min Act: -0.0000

Data Index: 453854 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.2122. Min Act: -0.0000

Data Index: 855699 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1004251 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.2128. Min Act: -0.0000

Data Index: 192176 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.6737. Min Range: -0.6737

Max Act: 0.2132. Min Act: -0.0001

Data Index: 866523 (C4 (Web Text))

Max Activating Token Index: 643