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

Dataset: The Pile

Neuron 5078 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: 0.2751. Min Range: -0.2751

Max Act: 0.2477. Min Act: -0.0000

Data Index: 922640 (The Pile)

Max Activating Token Index: 639

Text #1

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2280. Min Act: -0.0000

Data Index: 288516 (The Pile)

Max Activating Token Index: 950

Text #2

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1438028 (The Pile)

Max Activating Token Index: 897

Text #3

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1502480 (The Pile)

Max Activating Token Index: 806

Text #4

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2428. Min Act: -0.0000

Data Index: 1148141 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1905542 (The Pile)

Max Activating Token Index: 699

Text #6

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2278. Min Act: -0.0000

Data Index: 306830 (The Pile)

Max Activating Token Index: 960

Text #7

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2159. Min Act: -0.0000

Data Index: 573564 (The Pile)

Max Activating Token Index: 145

Text #8

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1143414 (The Pile)

Max Activating Token Index: 234

Text #9

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2178. Min Act: -0.0000

Data Index: 830089 (The Pile)

Max Activating Token Index: 567

Text #10

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2038. Min Act: -0.0000

Data Index: 414294 (The Pile)

Max Activating Token Index: 145

Text #11

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1074318 (The Pile)

Max Activating Token Index: 305

Text #12

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1647284 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1868. Min Act: -0.0000

Data Index: 89218 (The Pile)

Max Activating Token Index: 197

Text #14

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1930. Min Act: -0.0000

Data Index: 665745 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1997. Min Act: -0.0000

Data Index: 865550 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1918. Min Act: -0.0000

Data Index: 736743 (The Pile)

Max Activating Token Index: 625

Text #17

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1439666 (The Pile)

Max Activating Token Index: 383

Text #18

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1490588 (The Pile)

Max Activating Token Index: 194

Text #19

Max Range: 0.2751. Min Range: -0.2751

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1600325 (The Pile)

Max Activating Token Index: 87