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

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

Neuron 5063 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: 0.9879. Min Range: -0.9879

Max Act: 0.9879. Min Act: -0.0000

Data Index: 1073383 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.8873. Min Act: -0.0000

Data Index: 961870 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.9383. Min Act: -0.0000

Data Index: 1089589 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.8610. Min Act: -0.0000

Data Index: 47025 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.8970. Min Act: -0.0000

Data Index: 264230 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.8635. Min Act: -0.0000

Data Index: 359513 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.8663. Min Act: -0.0000

Data Index: 1165912 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1257615 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1149216 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.8065. Min Act: -0.0000

Data Index: 164612 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.7807. Min Act: -0.0000

Data Index: 929081 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.7760. Min Act: -0.0000

Data Index: 169358 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.8268. Min Act: -0.0000

Data Index: 367576 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1229427 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.7627. Min Act: -0.0000

Data Index: 651860 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.7862. Min Act: -0.0000

Data Index: 182330 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.8341. Min Act: -0.0000

Data Index: 400228 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.7639. Min Act: -0.0000

Data Index: 448745 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.8103. Min Act: -0.0000

Data Index: 1195751 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.9879. Min Range: -0.9879

Max Act: 0.8253. Min Act: -0.0000

Data Index: 112547 (C4 (Web Text))

Max Activating Token Index: 840