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

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

Neuron 5468 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.8146. Min Act: -0.0000

Data Index: 1467487 (Python Code)

Max Activating Token Index: 202

Text #1

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.8237. Min Act: -0.0000

Data Index: 1517212 (Python Code)

Max Activating Token Index: 848

Text #2

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1537593 (Python Code)

Max Activating Token Index: 830

Text #3

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6696. Min Act: -0.0000

Data Index: 1475685 (Python Code)

Max Activating Token Index: 588

Text #4

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1585973 (Python Code)

Max Activating Token Index: 915

Text #5

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1648969 (Python Code)

Max Activating Token Index: 592

Text #6

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6866. Min Act: -0.0000

Data Index: 1592144 (Python Code)

Max Activating Token Index: 897

Text #7

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1594944 (Python Code)

Max Activating Token Index: 149

Text #8

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1379612 (Python Code)

Max Activating Token Index: 668

Text #9

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6456. Min Act: -0.0000

Data Index: 1655046 (Python Code)

Max Activating Token Index: 642

Text #10

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1486856 (Python Code)

Max Activating Token Index: 934

Text #11

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1433636 (Python Code)

Max Activating Token Index: 343

Text #12

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1632580 (Python Code)

Max Activating Token Index: 724

Text #13

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1611970 (Python Code)

Max Activating Token Index: 829

Text #14

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5677. Min Act: -0.0000

Data Index: 1556642 (Python Code)

Max Activating Token Index: 719

Text #15

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1428583 (Python Code)

Max Activating Token Index: 733

Text #16

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6269. Min Act: -0.0000

Data Index: 1656291 (Python Code)

Max Activating Token Index: 221

Text #17

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1649404 (Python Code)

Max Activating Token Index: 475

Text #18

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1548001 (Python Code)

Max Activating Token Index: 84

Text #19

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1650643 (Python Code)

Max Activating Token Index: 485