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

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

Neuron 437 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1083. Min Range: -1.1083

Max Act: 1.0820. Min Act: -0.0001

Data Index: 537593 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 1.1083. Min Range: -1.1083

Max Act: 1.1083. Min Act: -0.0001

Data Index: 624680 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 1.1083. Min Range: -1.1083

Max Act: 1.0101. Min Act: -0.0001

Data Index: 887350 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 1.1083. Min Range: -1.1083

Max Act: 1.0060. Min Act: -0.0001

Data Index: 933902 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.9786. Min Act: -0.0001

Data Index: 32724 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.9545. Min Act: -0.0001

Data Index: 117915 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.9669. Min Act: -0.0001

Data Index: 693504 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.9093. Min Act: -0.0001

Data Index: 642218 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.9906. Min Act: -0.0001

Data Index: 583670 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.8693. Min Act: -0.0001

Data Index: 367475 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.8944. Min Act: -0.0001

Data Index: 153605 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.8806. Min Act: -0.0001

Data Index: 152570 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.8198. Min Act: -0.0001

Data Index: 1113003 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.8413. Min Act: -0.0001

Data Index: 594525 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.8773. Min Act: -0.0001

Data Index: 1245959 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.8528. Min Act: -0.0001

Data Index: 986299 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.8715. Min Act: -0.0001

Data Index: 842727 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.8401. Min Act: -0.0001

Data Index: 465938 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.8088. Min Act: -0.0001

Data Index: 128066 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.8078. Min Act: -0.0001

Data Index: 665341 (C4 (Web Text))

Max Activating Token Index: 385