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

Dataset: The Pile

Neuron 2594 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: 0.7043. Min Range: -0.7043

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1461583 (The Pile)

Max Activating Token Index: 78

Text #1

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.7043. Min Act: -0.0000

Data Index: 1207024 (The Pile)

Max Activating Token Index: 7

Text #2

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1042726 (The Pile)

Max Activating Token Index: 158

Text #3

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.6561. Min Act: -0.0000

Data Index: 196068 (The Pile)

Max Activating Token Index: 465

Text #4

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.6563. Min Act: -0.0000

Data Index: 810063 (The Pile)

Max Activating Token Index: 765

Text #5

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.6731. Min Act: -0.0000

Data Index: 32778 (The Pile)

Max Activating Token Index: 63

Text #6

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.6176. Min Act: -0.0000

Data Index: 1922416 (The Pile)

Max Activating Token Index: 335

Text #7

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.6126. Min Act: -0.0000

Data Index: 280959 (The Pile)

Max Activating Token Index: 807

Text #8

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.6070. Min Act: -0.0000

Data Index: 5980 (The Pile)

Max Activating Token Index: 124

Text #9

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1511039 (The Pile)

Max Activating Token Index: 78

Text #10

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5245. Min Act: -0.0000

Data Index: 147116 (The Pile)

Max Activating Token Index: 353

Text #11

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1224211 (The Pile)

Max Activating Token Index: 503

Text #12

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5191. Min Act: -0.0000

Data Index: 422316 (The Pile)

Max Activating Token Index: 598

Text #13

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5131. Min Act: -0.0000

Data Index: 863389 (The Pile)

Max Activating Token Index: 396

Text #14

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1240352 (The Pile)

Max Activating Token Index: 722

Text #15

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.4726. Min Act: -0.0000

Data Index: 382585 (The Pile)

Max Activating Token Index: 835

Text #16

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5436. Min Act: -0.0000

Data Index: 1211969 (The Pile)

Max Activating Token Index: 413

Text #17

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5044. Min Act: -0.0000

Data Index: 685919 (The Pile)

Max Activating Token Index: 130

Text #18

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.5190. Min Act: -0.0000

Data Index: 976142 (The Pile)

Max Activating Token Index: 67

Text #19

Max Range: 0.7043. Min Range: -0.7043

Max Act: 0.4887. Min Act: -0.0000

Data Index: 372165 (The Pile)

Max Activating Token Index: 238