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

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

Neuron 3482 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1006986 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0740. Min Act: -0.0001

Data Index: 945000 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0754. Min Act: -0.0001

Data Index: 591392 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1381312 (Python Code)

Max Activating Token Index: 950

Text #4

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1160955 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0704. Min Act: -0.0000

Data Index: 1487810 (Python Code)

Max Activating Token Index: 189

Text #6

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0663. Min Act: -0.0000

Data Index: 215884 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0643. Min Act: -0.0000

Data Index: 1438341 (Python Code)

Max Activating Token Index: 695

Text #8

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1101192 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0666. Min Act: -0.0001

Data Index: 526433 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0670. Min Act: -0.0001

Data Index: 906679 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0550. Min Act: -0.0000

Data Index: 1025466 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0647. Min Act: -0.0001

Data Index: 642868 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0584. Min Act: -0.0001

Data Index: 135676 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0575. Min Act: -0.0000

Data Index: 1471604 (Python Code)

Max Activating Token Index: 139

Text #15

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1350498 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0551. Min Act: -0.0000

Data Index: 597300 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0624. Min Act: -0.0001

Data Index: 768321 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0601. Min Act: -0.0001

Data Index: 281009 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0578. Min Act: -0.0001

Data Index: 950848 (C4 (Web Text))

Max Activating Token Index: 779