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

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

Neuron 3689 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3693. Min Range: -2.3693

Max Act: 2.3693. Min Act: -0.0000

Data Index: 799921 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 2.3693. Min Range: -2.3693

Max Act: 2.0601. Min Act: -0.0000

Data Index: 859158 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 2.3693. Min Range: -2.3693

Max Act: 2.0616. Min Act: -0.0000

Data Index: 118243 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 2.3693. Min Range: -2.3693

Max Act: 2.0093. Min Act: -0.0000

Data Index: 71827 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 2.3693. Min Range: -2.3693

Max Act: 1.9344. Min Act: -0.0000

Data Index: 1030304 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 2.3693. Min Range: -2.3693

Max Act: 1.9071. Min Act: -0.0000

Data Index: 454864 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 2.3693. Min Range: -2.3693

Max Act: 1.8110. Min Act: -0.0000

Data Index: 249946 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 2.3693. Min Range: -2.3693

Max Act: 1.8214. Min Act: -0.0000

Data Index: 610333 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 2.3693. Min Range: -2.3693

Max Act: 1.7107. Min Act: -0.0000

Data Index: 1191725 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 2.3693. Min Range: -2.3693

Max Act: 1.8043. Min Act: -0.0000

Data Index: 978902 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 2.3693. Min Range: -2.3693

Max Act: 1.8995. Min Act: -0.0000

Data Index: 170349 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 2.3693. Min Range: -2.3693

Max Act: 1.7963. Min Act: -0.0000

Data Index: 808708 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 2.3693. Min Range: -2.3693

Max Act: 1.7926. Min Act: -0.0000

Data Index: 669610 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 2.3693. Min Range: -2.3693

Max Act: 1.7059. Min Act: -0.0000

Data Index: 399585 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 2.3693. Min Range: -2.3693

Max Act: 1.6533. Min Act: -0.0000

Data Index: 477426 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 2.3693. Min Range: -2.3693

Max Act: 1.5474. Min Act: -0.0000

Data Index: 578697 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 2.3693. Min Range: -2.3693

Max Act: 1.7395. Min Act: -0.0000

Data Index: 212746 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 2.3693. Min Range: -2.3693

Max Act: 1.7095. Min Act: -0.0000

Data Index: 1184407 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 2.3693. Min Range: -2.3693

Max Act: 1.5349. Min Act: -0.0000

Data Index: 902790 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 2.3693. Min Range: -2.3693

Max Act: 1.5274. Min Act: -0.0000

Data Index: 1081203 (C4 (Web Text))

Max Activating Token Index: 330