Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1975 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2666. Min Act: -0.0002

Data Index: 691480 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2630. Min Act: -0.0002

Data Index: 603253 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2508. Min Act: -0.0002

Data Index: 964521 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2453. Min Act: -0.0002

Data Index: 631187 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2397. Min Act: -0.0002

Data Index: 195474 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2380. Min Act: -0.0002

Data Index: 891828 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2498. Min Act: -0.0002

Data Index: 493997 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2223. Min Act: -0.0002

Data Index: 1270398 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2258. Min Act: -0.0002

Data Index: 125185 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2326. Min Act: -0.0002

Data Index: 693986 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2218. Min Act: -0.0002

Data Index: 1074433 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2273. Min Act: -0.0002

Data Index: 608872 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2177. Min Act: -0.0002

Data Index: 545066 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2163. Min Act: -0.0002

Data Index: 839040 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2146. Min Act: -0.0002

Data Index: 1048650 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.1850. Min Act: -0.0002

Data Index: 1048525 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2134. Min Act: -0.0002

Data Index: 927696 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2125. Min Act: -0.0002

Data Index: 738853 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2040. Min Act: -0.0002

Data Index: 491668 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.2666. Min Range: -0.2666

Max Act: 0.2178. Min Act: -0.0002

Data Index: 1121358 (C4 (Web Text))

Max Activating Token Index: 832