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

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

Neuron 4362 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.6998. Min Act: -0.0000

Data Index: 56633 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.7758. Min Act: -0.0000

Data Index: 1141789 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.4987. Min Act: -0.0000

Data Index: 964406 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.6918. Min Act: -0.0000

Data Index: 451459 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.5467. Min Act: -0.0000

Data Index: 1286254 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.5663. Min Act: -0.0000

Data Index: 1134460 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.3781. Min Act: -0.0000

Data Index: 64344 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.4944. Min Act: -0.0000

Data Index: 600659 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.4640. Min Act: -0.0000

Data Index: 144918 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.5433. Min Act: -0.0000

Data Index: 462938 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.4246. Min Act: -0.0000

Data Index: 1102906 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.4610. Min Act: -0.0000

Data Index: 771201 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.4035. Min Act: -0.0000

Data Index: 235448 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.4602. Min Act: -0.0000

Data Index: 400051 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.5020. Min Act: -0.0000

Data Index: 417845 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.5334. Min Act: -0.0000

Data Index: 997402 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.5204. Min Act: -0.0000

Data Index: 741868 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.4800. Min Act: -0.0000

Data Index: 443361 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.4188. Min Act: -0.0000

Data Index: 978268 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 2.7758. Min Range: -2.7758

Max Act: 2.3760. Min Act: -0.0000

Data Index: 258899 (C4 (Web Text))

Max Activating Token Index: 1006