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

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

Neuron 2457 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: 2.4172. Min Range: -2.4172

Max Act: 2.4172. Min Act: -0.0000

Data Index: 176008 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 2.4172. Min Range: -2.4172

Max Act: 2.1957. Min Act: -0.0000

Data Index: 149559 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 2.4172. Min Range: -2.4172

Max Act: 2.1636. Min Act: -0.0000

Data Index: 602209 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 2.4172. Min Range: -2.4172

Max Act: 2.2765. Min Act: -0.0000

Data Index: 1029696 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 2.4172. Min Range: -2.4172

Max Act: 2.1209. Min Act: -0.0000

Data Index: 47078 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 2.4172. Min Range: -2.4172

Max Act: 2.2917. Min Act: -0.0000

Data Index: 1091866 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 2.4172. Min Range: -2.4172

Max Act: 1.9993. Min Act: -0.0000

Data Index: 482459 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 2.4172. Min Range: -2.4172

Max Act: 1.8576. Min Act: -0.0000

Data Index: 1234598 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 2.4172. Min Range: -2.4172

Max Act: 2.0673. Min Act: -0.0000

Data Index: 1215872 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 2.4172. Min Range: -2.4172

Max Act: 1.8090. Min Act: -0.0000

Data Index: 923902 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 2.4172. Min Range: -2.4172

Max Act: 1.9032. Min Act: -0.0000

Data Index: 527743 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 2.4172. Min Range: -2.4172

Max Act: 2.0106. Min Act: -0.0000

Data Index: 851615 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 2.4172. Min Range: -2.4172

Max Act: 1.7499. Min Act: -0.0000

Data Index: 1247244 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 2.4172. Min Range: -2.4172

Max Act: 2.0314. Min Act: -0.0000

Data Index: 377044 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 2.4172. Min Range: -2.4172

Max Act: 1.8229. Min Act: -0.0000

Data Index: 320316 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 2.4172. Min Range: -2.4172

Max Act: 1.7751. Min Act: -0.0000

Data Index: 1302443 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 2.4172. Min Range: -2.4172

Max Act: 1.6506. Min Act: -0.0000

Data Index: 365320 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 2.4172. Min Range: -2.4172

Max Act: 1.6533. Min Act: -0.0000

Data Index: 512283 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 2.4172. Min Range: -2.4172

Max Act: 1.7402. Min Act: -0.0000

Data Index: 920479 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 2.4172. Min Range: -2.4172

Max Act: 1.7365. Min Act: -0.0000

Data Index: 468710 (C4 (Web Text))

Max Activating Token Index: 752