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

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

Neuron 1726 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1541154 (Python Code)

Max Activating Token Index: 413

Text #1

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1392340 (Python Code)

Max Activating Token Index: 73

Text #2

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0615. Min Act: -0.0003

Data Index: 1124876 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1439789 (Python Code)

Max Activating Token Index: 222

Text #4

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1455289 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1313090 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1389763 (Python Code)

Max Activating Token Index: 66

Text #7

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0567. Min Act: -0.0003

Data Index: 371655 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1496466 (Python Code)

Max Activating Token Index: 932

Text #9

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0549. Min Act: -0.0003

Data Index: 402505 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0554. Min Act: -0.0003

Data Index: 71254 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1607536 (Python Code)

Max Activating Token Index: 137

Text #12

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1258931 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1477444 (Python Code)

Max Activating Token Index: 930

Text #14

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1645929 (Python Code)

Max Activating Token Index: 829

Text #15

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0562. Min Act: -0.0003

Data Index: 1520029 (Python Code)

Max Activating Token Index: 181

Text #16

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1442690 (Python Code)

Max Activating Token Index: 87

Text #17

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0557. Min Act: -0.0003

Data Index: 1537128 (Python Code)

Max Activating Token Index: 872

Text #18

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1638594 (Python Code)

Max Activating Token Index: 973

Text #19

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0528. Min Act: -0.0003

Data Index: 478389 (C4 (Web Text))

Max Activating Token Index: 214