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

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

Neuron 3385 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.9828. Min Act: -0.0001

Data Index: 243752 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.9552. Min Act: -0.0002

Data Index: 1021617 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.9500. Min Act: -0.0001

Data Index: 1075892 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 1.0095. Min Range: -1.0095

Max Act: 1.0095. Min Act: -0.0001

Data Index: 494852 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.9144. Min Act: -0.0001

Data Index: 1095226 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.9237. Min Act: -0.0001

Data Index: 1294374 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8805. Min Act: -0.0001

Data Index: 844242 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.9017. Min Act: -0.0001

Data Index: 533875 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.9002. Min Act: -0.0001

Data Index: 790988 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.9047. Min Act: -0.0001

Data Index: 419951 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8071. Min Act: -0.0001

Data Index: 676614 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8682. Min Act: -0.0001

Data Index: 510130 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8864. Min Act: -0.0001

Data Index: 1264335 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.7943. Min Act: -0.0001

Data Index: 1329481 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8361. Min Act: -0.0001

Data Index: 926586 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8024. Min Act: -0.0001

Data Index: 1124992 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8066. Min Act: -0.0001

Data Index: 419173 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8786. Min Act: -0.0001

Data Index: 658172 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8456. Min Act: -0.0002

Data Index: 1311849 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 1.0095. Min Range: -1.0095

Max Act: 0.8072. Min Act: -0.0001

Data Index: 112528 (C4 (Web Text))

Max Activating Token Index: 235