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

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

Neuron 1323 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: 0.4670. Min Range: -0.4670

Max Act: 0.4670. Min Act: -0.0000

Data Index: 5516 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.4247. Min Act: -0.0000

Data Index: 822759 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1240471 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.4155. Min Act: -0.0000

Data Index: 102945 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.4026. Min Act: -0.0000

Data Index: 496302 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1073480 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.3803. Min Act: -0.0000

Data Index: 982486 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.3689. Min Act: -0.0000

Data Index: 1033200 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.3846. Min Act: -0.0000

Data Index: 862221 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.3579. Min Act: -0.0000

Data Index: 887958 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.3582. Min Act: -0.0000

Data Index: 312798 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.3558. Min Act: -0.0000

Data Index: 526152 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.3672. Min Act: -0.0000

Data Index: 771969 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1047371 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.3520. Min Act: -0.0000

Data Index: 550045 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.3698. Min Act: -0.0000

Data Index: 3825 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.3585. Min Act: -0.0000

Data Index: 601662 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.3558. Min Act: -0.0000

Data Index: 652966 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1316056 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.4670. Min Range: -0.4670

Max Act: 0.3598. Min Act: -0.0000

Data Index: 549935 (C4 (Web Text))

Max Activating Token Index: 512