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

Dataset: The Pile

Neuron 3882 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1964. Min Act: -0.0000

Data Index: 445752 (The Pile)

Max Activating Token Index: 658

Text #1

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1342. Min Act: -0.0000

Data Index: 104691 (The Pile)

Max Activating Token Index: 85

Text #2

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1387. Min Act: -0.0000

Data Index: 214425 (The Pile)

Max Activating Token Index: 1018

Text #3

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1374. Min Act: -0.0000

Data Index: 785445 (The Pile)

Max Activating Token Index: 152

Text #4

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1239. Min Act: -0.0000

Data Index: 482144 (The Pile)

Max Activating Token Index: 906

Text #5

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1248. Min Act: -0.0000

Data Index: 586645 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1179. Min Act: -0.0000

Data Index: 395838 (The Pile)

Max Activating Token Index: 722

Text #7

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1165. Min Act: -0.0000

Data Index: 1080000 (The Pile)

Max Activating Token Index: 874

Text #8

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1134. Min Act: -0.0000

Data Index: 501030 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1201. Min Act: -0.0000

Data Index: 1206576 (The Pile)

Max Activating Token Index: 45

Text #10

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1158. Min Act: -0.0000

Data Index: 1746654 (The Pile)

Max Activating Token Index: 513

Text #11

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1222. Min Act: -0.0000

Data Index: 935474 (The Pile)

Max Activating Token Index: 181

Text #12

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1855196 (The Pile)

Max Activating Token Index: 256

Text #13

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1122. Min Act: -0.0000

Data Index: 1725225 (The Pile)

Max Activating Token Index: 1008

Text #14

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1128. Min Act: -0.0000

Data Index: 42788 (The Pile)

Max Activating Token Index: 494

Text #15

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1269531 (The Pile)

Max Activating Token Index: 884

Text #16

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1670994 (The Pile)

Max Activating Token Index: 208

Text #17

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1130. Min Act: -0.0000

Data Index: 1457191 (The Pile)

Max Activating Token Index: 334

Text #18

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1075. Min Act: -0.0000

Data Index: 368066 (The Pile)

Max Activating Token Index: 936

Text #19

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.0972. Min Act: -0.0000

Data Index: 308491 (The Pile)

Max Activating Token Index: 908