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

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

Neuron 527 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1187. Min Act: -0.0003

Data Index: 236558 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1146. Min Act: -0.0003

Data Index: 1212710 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1167. Min Act: -0.0003

Data Index: 208815 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1040. Min Act: -0.0003

Data Index: 462456 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1068. Min Act: -0.0003

Data Index: 456062 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1059. Min Act: -0.0003

Data Index: 1187324 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0940. Min Act: -0.0003

Data Index: 2695 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0938. Min Act: -0.0003

Data Index: 1154643 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0993. Min Act: -0.0003

Data Index: 233462 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0925. Min Act: -0.0003

Data Index: 95023 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0949. Min Act: -0.0003

Data Index: 531658 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0907. Min Act: -0.0003

Data Index: 309479 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0976. Min Act: -0.0003

Data Index: 118815 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0938. Min Act: -0.0003

Data Index: 248365 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0921. Min Act: -0.0003

Data Index: 344740 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0912. Min Act: -0.0003

Data Index: 564631 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0912. Min Act: -0.0003

Data Index: 448214 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0972. Min Act: -0.0003

Data Index: 477586 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0936. Min Act: -0.0003

Data Index: 137822 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0862. Min Act: -0.0003

Data Index: 611437 (C4 (Web Text))

Max Activating Token Index: 457