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

Dataset: The Pile

Neuron 3026 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: 0.1439. Min Range: -0.1439

Max Act: 0.1439. Min Act: 0.0001

Data Index: 175171 (The Pile)

Max Activating Token Index: 3

Text #1

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1388. Min Act: -0.0000

Data Index: 1056382 (The Pile)

Max Activating Token Index: 16

Text #2

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1306. Min Act: -0.0000

Data Index: 496897 (The Pile)

Max Activating Token Index: 11

Text #3

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1282. Min Act: 0.0000

Data Index: 1735593 (The Pile)

Max Activating Token Index: 9

Text #4

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1282. Min Act: -0.0000

Data Index: 1895160 (The Pile)

Max Activating Token Index: 11

Text #5

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1377430 (The Pile)

Max Activating Token Index: 26

Text #6

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1236. Min Act: 0.0000

Data Index: 342945 (The Pile)

Max Activating Token Index: 13

Text #7

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1198. Min Act: 0.0001

Data Index: 683332 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1183. Min Act: -0.0000

Data Index: 439620 (The Pile)

Max Activating Token Index: 21

Text #9

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1213. Min Act: 0.0001

Data Index: 786170 (The Pile)

Max Activating Token Index: 6

Text #10

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1150. Min Act: 0.0000

Data Index: 975855 (The Pile)

Max Activating Token Index: 18

Text #11

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1130. Min Act: 0.0000

Data Index: 1444401 (The Pile)

Max Activating Token Index: 6

Text #12

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1120. Min Act: 0.0000

Data Index: 1503954 (The Pile)

Max Activating Token Index: 58

Text #13

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1110. Min Act: -0.0000

Data Index: 728342 (The Pile)

Max Activating Token Index: 6

Text #14

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1112. Min Act: 0.0001

Data Index: 1525069 (The Pile)

Max Activating Token Index: 6

Text #15

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1139. Min Act: 0.0000

Data Index: 1252987 (The Pile)

Max Activating Token Index: 2

Text #16

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1089. Min Act: -0.0000

Data Index: 728316 (The Pile)

Max Activating Token Index: 15

Text #17

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1083. Min Act: 0.0001

Data Index: 208093 (The Pile)

Max Activating Token Index: 16

Text #18

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1075. Min Act: 0.0000

Data Index: 279773 (The Pile)

Max Activating Token Index: 24

Text #19

Max Range: 0.1439. Min Range: -0.1439

Max Act: 0.1067. Min Act: -0.0000

Data Index: 140956 (The Pile)

Max Activating Token Index: 6