Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2724 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1155. Min Act: -0.0001

Data Index: 5379 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1190. Min Act: -0.0001

Data Index: 645275 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1255616 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1059. Min Act: -0.0001

Data Index: 996523 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1036. Min Act: -0.0000

Data Index: 497233 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1084. Min Act: -0.0001

Data Index: 1028818 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1078. Min Act: -0.0001

Data Index: 854734 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1075. Min Act: 0.0002

Data Index: 211970 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1032. Min Act: 0.0002

Data Index: 1126547 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1029. Min Act: -0.0001

Data Index: 1133168 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1017. Min Act: -0.0000

Data Index: 950031 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1188614 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0952. Min Act: -0.0001

Data Index: 324215 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0991. Min Act: -0.0001

Data Index: 1093507 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1018. Min Act: -0.0001

Data Index: 444282 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0948. Min Act: -0.0001

Data Index: 689303 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0972. Min Act: -0.0001

Data Index: 659536 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0976. Min Act: -0.0001

Data Index: 529206 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0998. Min Act: -0.0001

Data Index: 576936 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0970. Min Act: -0.0001

Data Index: 115910 (C4 (Web Text))

Max Activating Token Index: 522