Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1503 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.9504. Min Act: -0.0000

Data Index: 254010 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.6581. Min Act: -0.0000

Data Index: 1119638 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.5074. Min Act: -0.0000

Data Index: 1145554 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.4691. Min Act: -0.0000

Data Index: 466343 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.4642. Min Act: -0.0000

Data Index: 1150244 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.4834. Min Act: -0.0000

Data Index: 486597 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.2214. Min Act: -0.0000

Data Index: 94778 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.4594. Min Act: -0.0000

Data Index: 1283444 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.2816. Min Act: -0.0000

Data Index: 606241 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.2734. Min Act: -0.0000

Data Index: 389991 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.0709. Min Act: -0.0000

Data Index: 119532 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.0622. Min Act: -0.0000

Data Index: 564108 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.1819. Min Act: -0.0000

Data Index: 274933 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.0346. Min Act: -0.0000

Data Index: 753006 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.2730. Min Act: -0.0000

Data Index: 732355 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.1094. Min Act: -0.0000

Data Index: 682219 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.1125. Min Act: -0.0000

Data Index: 127700 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.1113. Min Act: -0.0000

Data Index: 702632 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 2.9504. Min Range: -2.9504

Max Act: 2.0846. Min Act: -0.0000

Data Index: 504669 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 2.9504. Min Range: -2.9504

Max Act: 1.9660. Min Act: -0.0000

Data Index: 120433 (C4 (Web Text))

Max Activating Token Index: 983