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

Dataset: The Pile

Neuron 3510 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2266. Min Range: -1.2266

Max Act: 1.2266. Min Act: -0.0000

Data Index: 135045 (The Pile)

Max Activating Token Index: 960

Text #1

Max Range: 1.2266. Min Range: -1.2266

Max Act: 1.1697. Min Act: -0.0000

Data Index: 869728 (The Pile)

Max Activating Token Index: 340

Text #2

Max Range: 1.2266. Min Range: -1.2266

Max Act: 1.0376. Min Act: -0.0000

Data Index: 282925 (The Pile)

Max Activating Token Index: 280

Text #3

Max Range: 1.2266. Min Range: -1.2266

Max Act: 1.0321. Min Act: -0.0000

Data Index: 1203550 (The Pile)

Max Activating Token Index: 262

Text #4

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.9901. Min Act: -0.0000

Data Index: 1589707 (The Pile)

Max Activating Token Index: 266

Text #5

Max Range: 1.2266. Min Range: -1.2266

Max Act: 1.0429. Min Act: -0.0000

Data Index: 859179 (The Pile)

Max Activating Token Index: 600

Text #6

Max Range: 1.2266. Min Range: -1.2266

Max Act: 1.0106. Min Act: -0.0000

Data Index: 777457 (The Pile)

Max Activating Token Index: 323

Text #7

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1760588 (The Pile)

Max Activating Token Index: 50

Text #8

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.9733. Min Act: -0.0000

Data Index: 1224953 (The Pile)

Max Activating Token Index: 8

Text #9

Max Range: 1.2266. Min Range: -1.2266

Max Act: 1.0103. Min Act: -0.0000

Data Index: 1458258 (The Pile)

Max Activating Token Index: 147

Text #10

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1972677 (The Pile)

Max Activating Token Index: 817

Text #11

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.9553. Min Act: -0.0000

Data Index: 502414 (The Pile)

Max Activating Token Index: 850

Text #12

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.9596. Min Act: -0.0000

Data Index: 1631813 (The Pile)

Max Activating Token Index: 918

Text #13

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1046513 (The Pile)

Max Activating Token Index: 669

Text #14

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.9254. Min Act: -0.0000

Data Index: 347285 (The Pile)

Max Activating Token Index: 947

Text #15

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.9128. Min Act: -0.0000

Data Index: 958032 (The Pile)

Max Activating Token Index: 203

Text #16

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1053456 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1076118 (The Pile)

Max Activating Token Index: 685

Text #18

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.9165. Min Act: -0.0000

Data Index: 1386466 (The Pile)

Max Activating Token Index: 53

Text #19

Max Range: 1.2266. Min Range: -1.2266

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1454307 (The Pile)

Max Activating Token Index: 773