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

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

Neuron 2997 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: 0.6290. Min Range: -0.6290

Max Act: 0.6010. Min Act: -0.0000

Data Index: 814259 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5840. Min Act: -0.0000

Data Index: 887919 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.6290. Min Act: -0.0000

Data Index: 926799 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5067. Min Act: -0.0000

Data Index: 384744 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5109. Min Act: -0.0000

Data Index: 579886 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5076. Min Act: -0.0000

Data Index: 135403 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4913. Min Act: -0.0000

Data Index: 645941 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.5455. Min Act: -0.0000

Data Index: 508696 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4623. Min Act: -0.0000

Data Index: 252960 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4608. Min Act: -0.0000

Data Index: 816327 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1355793 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4672. Min Act: -0.0000

Data Index: 605785 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4447. Min Act: -0.0000

Data Index: 403603 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4606. Min Act: -0.0000

Data Index: 684214 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1291196 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4414. Min Act: -0.0000

Data Index: 1298936 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4296. Min Act: -0.0000

Data Index: 443069 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4434. Min Act: -0.0000

Data Index: 880827 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.3970. Min Act: -0.0000

Data Index: 144215 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.6290. Min Range: -0.6290

Max Act: 0.4231. Min Act: -0.0000

Data Index: 507487 (C4 (Web Text))

Max Activating Token Index: 930