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

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

Neuron 1617 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5088. Min Range: -2.5088

Max Act: 2.5088. Min Act: -0.0000

Data Index: 1230714 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 2.5088. Min Range: -2.5088

Max Act: 2.1354. Min Act: -0.0000

Data Index: 327023 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 2.5088. Min Range: -2.5088

Max Act: 2.1644. Min Act: -0.0000

Data Index: 596224 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 2.5088. Min Range: -2.5088

Max Act: 1.8594. Min Act: -0.0000

Data Index: 1248767 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 2.5088. Min Range: -2.5088

Max Act: 2.0572. Min Act: -0.0000

Data Index: 379878 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 2.5088. Min Range: -2.5088

Max Act: 1.7808. Min Act: -0.0000

Data Index: 919712 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 2.5088. Min Range: -2.5088

Max Act: 1.7741. Min Act: -0.0000

Data Index: 314907 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 2.5088. Min Range: -2.5088

Max Act: 1.6634. Min Act: -0.0000

Data Index: 1131052 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 2.5088. Min Range: -2.5088

Max Act: 1.6081. Min Act: -0.0000

Data Index: 92751 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 2.5088. Min Range: -2.5088

Max Act: 1.5457. Min Act: -0.0000

Data Index: 118477 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 2.5088. Min Range: -2.5088

Max Act: 1.5021. Min Act: -0.0000

Data Index: 720674 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 2.5088. Min Range: -2.5088

Max Act: 1.6266. Min Act: -0.0000

Data Index: 173446 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 2.5088. Min Range: -2.5088

Max Act: 1.2974. Min Act: -0.0000

Data Index: 1231672 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 2.5088. Min Range: -2.5088

Max Act: 1.3509. Min Act: -0.0000

Data Index: 250188 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 2.5088. Min Range: -2.5088

Max Act: 1.3600. Min Act: -0.0000

Data Index: 432005 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 2.5088. Min Range: -2.5088

Max Act: 1.3463. Min Act: -0.0000

Data Index: 506896 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 2.5088. Min Range: -2.5088

Max Act: 1.4888. Min Act: -0.0000

Data Index: 251157 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 2.5088. Min Range: -2.5088

Max Act: 1.3036. Min Act: -0.0000

Data Index: 342536 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 2.5088. Min Range: -2.5088

Max Act: 1.3733. Min Act: -0.0000

Data Index: 1024764 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 2.5088. Min Range: -2.5088

Max Act: 1.2132. Min Act: -0.0000

Data Index: 127207 (C4 (Web Text))

Max Activating Token Index: 924