Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1341 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.7138. Min Act: -0.0000

Data Index: 1642496 (The Pile)

Max Activating Token Index: 865

Text #1

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1448337 (The Pile)

Max Activating Token Index: 985

Text #2

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1524580 (The Pile)

Max Activating Token Index: 833

Text #3

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.7017. Min Act: 0.0000

Data Index: 59046 (The Pile)

Max Activating Token Index: 365

Text #4

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1962766 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6851. Min Act: -0.0000

Data Index: 1966622 (The Pile)

Max Activating Token Index: 117

Text #6

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6727. Min Act: -0.0000

Data Index: 979675 (The Pile)

Max Activating Token Index: 819

Text #7

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1644194 (The Pile)

Max Activating Token Index: 416

Text #8

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6110. Min Act: -0.0000

Data Index: 351503 (The Pile)

Max Activating Token Index: 267

Text #9

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6425. Min Act: -0.0000

Data Index: 1577556 (The Pile)

Max Activating Token Index: 412

Text #10

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1117340 (The Pile)

Max Activating Token Index: 230

Text #11

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6176. Min Act: -0.0000

Data Index: 515993 (The Pile)

Max Activating Token Index: 580

Text #12

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5796. Min Act: -0.0000

Data Index: 332096 (The Pile)

Max Activating Token Index: 944

Text #13

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1039616 (The Pile)

Max Activating Token Index: 283

Text #14

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6073. Min Act: -0.0000

Data Index: 1922951 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5846. Min Act: 0.0000

Data Index: 969952 (The Pile)

Max Activating Token Index: 570

Text #16

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1409487 (The Pile)

Max Activating Token Index: 541

Text #17

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6034. Min Act: -0.0000

Data Index: 198078 (The Pile)

Max Activating Token Index: 967

Text #18

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5658. Min Act: -0.0000

Data Index: 243130 (The Pile)

Max Activating Token Index: 283

Text #19

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5620. Min Act: -0.0000

Data Index: 19364 (The Pile)

Max Activating Token Index: 366