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

Dataset: The Pile

Neuron 4519 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1371560 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1101. Min Act: 0.0000

Data Index: 1356145 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1048. Min Act: -0.0000

Data Index: 1632957 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1164194 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0954. Min Act: -0.0000

Data Index: 257280 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0922. Min Act: -0.0000

Data Index: 809154 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1327430 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1179224 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1592476 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1563282 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0895. Min Act: -0.0000

Data Index: 640781 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0884. Min Act: -0.0000

Data Index: 39501 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0876. Min Act: -0.0000

Data Index: 94652 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0871. Min Act: -0.0000

Data Index: 346681 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0869. Min Act: -0.0000

Data Index: 400832 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0860. Min Act: -0.0000

Data Index: 1289309 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0860. Min Act: -0.0000

Data Index: 1064870 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0849. Min Act: -0.0000

Data Index: 365233 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0846. Min Act: -0.0000

Data Index: 558327 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0844. Min Act: -0.0000

Data Index: 156134 (The Pile)

Max Activating Token Index: 1023