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

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

Neuron 3133 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.0843. Min Range: -1.0843

Max Act: 1.0843. Min Act: -0.0002

Data Index: 1328331 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 1.0843. Min Range: -1.0843

Max Act: 1.0470. Min Act: -0.0002

Data Index: 1272889 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 1.0843. Min Range: -1.0843

Max Act: 1.0211. Min Act: -0.0002

Data Index: 985578 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9761. Min Act: -0.0002

Data Index: 1452598 (Python Code)

Max Activating Token Index: 985

Text #4

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9772. Min Act: -0.0002

Data Index: 1476404 (Python Code)

Max Activating Token Index: 696

Text #5

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9673. Min Act: -0.0002

Data Index: 1406010 (Python Code)

Max Activating Token Index: 932

Text #6

Max Range: 1.0843. Min Range: -1.0843

Max Act: 1.0282. Min Act: -0.0002

Data Index: 1253505 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9651. Min Act: -0.0002

Data Index: 908479 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9655. Min Act: -0.0003

Data Index: 1274934 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9401. Min Act: -0.0002

Data Index: 1368153 (Python Code)

Max Activating Token Index: 676

Text #10

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9462. Min Act: -0.0002

Data Index: 1432187 (Python Code)

Max Activating Token Index: 926

Text #11

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9503. Min Act: -0.0002

Data Index: 1488789 (Python Code)

Max Activating Token Index: 833

Text #12

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9358. Min Act: -0.0002

Data Index: 1532689 (Python Code)

Max Activating Token Index: 1008

Text #13

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9417. Min Act: -0.0002

Data Index: 1331011 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9215. Min Act: -0.0002

Data Index: 1382568 (Python Code)

Max Activating Token Index: 965

Text #15

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9782. Min Act: -0.0002

Data Index: 1478234 (Python Code)

Max Activating Token Index: 1018

Text #16

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9539. Min Act: -0.0002

Data Index: 1267693 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9675. Min Act: -0.0002

Data Index: 1574644 (Python Code)

Max Activating Token Index: 645

Text #18

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9492. Min Act: -0.0002

Data Index: 987423 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 1.0843. Min Range: -1.0843

Max Act: 0.9570. Min Act: -0.0002

Data Index: 1464389 (Python Code)

Max Activating Token Index: 858