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

Dataset: The Pile

Neuron 2913 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: 0.2980. Min Range: -0.2980

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1286201 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2447. Min Act: -0.0000

Data Index: 260918 (The Pile)

Max Activating Token Index: 92

Text #2

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2284. Min Act: 0.0000

Data Index: 1079578 (The Pile)

Max Activating Token Index: 624

Text #3

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2421. Min Act: 0.0001

Data Index: 763734 (The Pile)

Max Activating Token Index: 682

Text #4

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2152. Min Act: 0.0000

Data Index: 1429811 (The Pile)

Max Activating Token Index: 899

Text #5

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2238. Min Act: -0.0000

Data Index: 521587 (The Pile)

Max Activating Token Index: 144

Text #6

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1167549 (The Pile)

Max Activating Token Index: 144

Text #7

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2095. Min Act: -0.0000

Data Index: 24359 (The Pile)

Max Activating Token Index: 782

Text #8

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.1973. Min Act: 0.0001

Data Index: 1684383 (The Pile)

Max Activating Token Index: 638

Text #9

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2094. Min Act: -0.0000

Data Index: 520134 (The Pile)

Max Activating Token Index: 542

Text #10

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2225. Min Act: -0.0000

Data Index: 697393 (The Pile)

Max Activating Token Index: 271

Text #11

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2068. Min Act: -0.0000

Data Index: 80533 (The Pile)

Max Activating Token Index: 68

Text #12

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2135. Min Act: -0.0000

Data Index: 1951955 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2042. Min Act: -0.0000

Data Index: 493573 (The Pile)

Max Activating Token Index: 748

Text #14

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2111. Min Act: 0.0000

Data Index: 354165 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2084. Min Act: -0.0000

Data Index: 727685 (The Pile)

Max Activating Token Index: 401

Text #16

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2071. Min Act: -0.0000

Data Index: 808199 (The Pile)

Max Activating Token Index: 1014

Text #17

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2118. Min Act: -0.0000

Data Index: 985905 (The Pile)

Max Activating Token Index: 985

Text #18

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2134. Min Act: -0.0000

Data Index: 105664 (The Pile)

Max Activating Token Index: 705

Text #19

Max Range: 0.2980. Min Range: -0.2980

Max Act: 0.2124. Min Act: -0.0000

Data Index: 921226 (The Pile)

Max Activating Token Index: 634