Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 502 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.5834. Min Act: -0.0003

Data Index: 1137965 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.5561. Min Act: -0.0003

Data Index: 68 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.5598. Min Act: -0.0002

Data Index: 795213 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.5397. Min Act: -0.0003

Data Index: 728787 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.5297. Min Act: -0.0003

Data Index: 1245058 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.5240. Min Act: -0.0003

Data Index: 1236941 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.5186. Min Act: -0.0003

Data Index: 1210977 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.5091. Min Act: -0.0003

Data Index: 693419 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4720. Min Act: -0.0003

Data Index: 1237755 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4935. Min Act: -0.0003

Data Index: 723963 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4903. Min Act: -0.0003

Data Index: 1231516 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.5044. Min Act: -0.0003

Data Index: 40923 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.5051. Min Act: -0.0003

Data Index: 368334 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.5054. Min Act: -0.0003

Data Index: 754559 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.5193. Min Act: -0.0003

Data Index: 18761 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.5299. Min Act: -0.0002

Data Index: 1280271 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4966. Min Act: -0.0003

Data Index: 434422 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.5070. Min Act: -0.0003

Data Index: 547455 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4904. Min Act: -0.0003

Data Index: 421546 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4915. Min Act: -0.0003

Data Index: 1130777 (C4 (Web Text))

Max Activating Token Index: 292