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

Dataset: The Pile

Neuron 2004 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: 0.1229. Min Range: -0.1229

Max Act: 0.1168. Min Act: -0.0000

Data Index: 1967558 (The Pile)

Max Activating Token Index: 895

Text #1

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1811877 (The Pile)

Max Activating Token Index: 963

Text #2

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1229. Min Act: -0.0000

Data Index: 4338 (The Pile)

Max Activating Token Index: 978

Text #3

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1222. Min Act: -0.0000

Data Index: 370558 (The Pile)

Max Activating Token Index: 533

Text #4

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1917356 (The Pile)

Max Activating Token Index: 753

Text #5

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1161. Min Act: -0.0000

Data Index: 1321812 (The Pile)

Max Activating Token Index: 271

Text #6

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1152. Min Act: -0.0000

Data Index: 1462289 (The Pile)

Max Activating Token Index: 477

Text #7

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1100. Min Act: -0.0000

Data Index: 1754471 (The Pile)

Max Activating Token Index: 462

Text #8

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1229737 (The Pile)

Max Activating Token Index: 501

Text #9

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1806129 (The Pile)

Max Activating Token Index: 179

Text #10

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1151072 (The Pile)

Max Activating Token Index: 1022

Text #11

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1052. Min Act: -0.0000

Data Index: 1547905 (The Pile)

Max Activating Token Index: 298

Text #12

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1870617 (The Pile)

Max Activating Token Index: 982

Text #13

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1051. Min Act: -0.0000

Data Index: 762904 (The Pile)

Max Activating Token Index: 805

Text #14

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1077. Min Act: -0.0000

Data Index: 1919832 (The Pile)

Max Activating Token Index: 589

Text #15

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1080. Min Act: -0.0000

Data Index: 919676 (The Pile)

Max Activating Token Index: 856

Text #16

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0994. Min Act: 0.0000

Data Index: 465981 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1383612 (The Pile)

Max Activating Token Index: 562

Text #18

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1333785 (The Pile)

Max Activating Token Index: 962

Text #19

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1009. Min Act: -0.0000

Data Index: 171961 (The Pile)

Max Activating Token Index: 1004