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

Dataset: The Pile

Neuron 2655 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1667. Min Act: -0.0000

Data Index: 180380 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1395. Min Act: -0.0000

Data Index: 124015 (The Pile)

Max Activating Token Index: 908

Text #2

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1462. Min Act: -0.0000

Data Index: 421502 (The Pile)

Max Activating Token Index: 725

Text #3

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1225283 (The Pile)

Max Activating Token Index: 552

Text #4

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1308. Min Act: -0.0000

Data Index: 1326171 (The Pile)

Max Activating Token Index: 327

Text #5

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1232. Min Act: -0.0000

Data Index: 1283739 (The Pile)

Max Activating Token Index: 139

Text #6

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1151. Min Act: -0.0000

Data Index: 186648 (The Pile)

Max Activating Token Index: 617

Text #7

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1044219 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1156. Min Act: -0.0000

Data Index: 120170 (The Pile)

Max Activating Token Index: 297

Text #9

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1149. Min Act: -0.0000

Data Index: 5341 (The Pile)

Max Activating Token Index: 265

Text #10

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1072. Min Act: -0.0000

Data Index: 1582515 (The Pile)

Max Activating Token Index: 780

Text #11

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1820627 (The Pile)

Max Activating Token Index: 818

Text #12

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1740601 (The Pile)

Max Activating Token Index: 899

Text #13

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1111. Min Act: -0.0000

Data Index: 1341423 (The Pile)

Max Activating Token Index: 690

Text #14

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1111. Min Act: -0.0000

Data Index: 1254705 (The Pile)

Max Activating Token Index: 256

Text #15

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1063. Min Act: -0.0000

Data Index: 740047 (The Pile)

Max Activating Token Index: 842

Text #16

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1137. Min Act: -0.0000

Data Index: 646304 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1128. Min Act: -0.0000

Data Index: 776618 (The Pile)

Max Activating Token Index: 514

Text #18

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1087. Min Act: -0.0000

Data Index: 1255644 (The Pile)

Max Activating Token Index: 170

Text #19

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1837819 (The Pile)

Max Activating Token Index: 319