Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4948 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1060492 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1405. Min Act: -0.0000

Data Index: 395624 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1309034 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1406. Min Act: -0.0000

Data Index: 830378 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1299. Min Act: -0.0000

Data Index: 375112 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1311. Min Act: -0.0000

Data Index: 35776 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1212. Min Act: -0.0000

Data Index: 1151615 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1284. Min Act: -0.0000

Data Index: 125602 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1183. Min Act: -0.0000

Data Index: 1009530 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1221. Min Act: -0.0000

Data Index: 882601 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1200. Min Act: -0.0000

Data Index: 912519 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1121. Min Act: -0.0000

Data Index: 339895 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1025. Min Act: -0.0000

Data Index: 198396 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1170. Min Act: -0.0000

Data Index: 285725 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1070. Min Act: -0.0000

Data Index: 965924 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1114. Min Act: -0.0000

Data Index: 26932 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1098. Min Act: -0.0000

Data Index: 1041082 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1086. Min Act: -0.0000

Data Index: 551452 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1259266 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 0.1780. Min Range: -0.1780

Max Act: 0.1052. Min Act: -0.0000

Data Index: 341543 (C4 (Web Text))

Max Activating Token Index: 1019