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

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

Neuron 3807 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0568. Min Range: -2.0568

Max Act: 2.0568. Min Act: -0.0000

Data Index: 494381 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9572. Min Act: -0.0000

Data Index: 662175 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9532. Min Act: -0.0000

Data Index: 1248112 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.8977. Min Act: -0.0000

Data Index: 333410 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9067. Min Act: -0.0000

Data Index: 180975 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.7792. Min Act: -0.0000

Data Index: 857443 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.9579. Min Act: -0.0000

Data Index: 452306 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.8453. Min Act: -0.0000

Data Index: 1046596 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.7143. Min Act: -0.0000

Data Index: 799474 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.6667. Min Act: -0.0000

Data Index: 464658 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.6264. Min Act: -0.0000

Data Index: 411223 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.4697. Min Act: -0.0000

Data Index: 607903 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.6286. Min Act: -0.0000

Data Index: 223597 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.5576. Min Act: -0.0000

Data Index: 931095 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.5518. Min Act: -0.0000

Data Index: 732251 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.6324. Min Act: -0.0000

Data Index: 778299 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.4307. Min Act: -0.0000

Data Index: 882899 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.5073. Min Act: -0.0000

Data Index: 152655 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.5036. Min Act: -0.0000

Data Index: 439923 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 2.0568. Min Range: -2.0568

Max Act: 1.4905. Min Act: -0.0000

Data Index: 1121301 (C4 (Web Text))

Max Activating Token Index: 575