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

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

Neuron 4191 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1554. Min Range: -1.1554

Max Act: 1.1554. Min Act: -0.0000

Data Index: 164595 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1434515 (Python Code)

Max Activating Token Index: 444

Text #2

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1439423 (Python Code)

Max Activating Token Index: 492

Text #3

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1538600 (Python Code)

Max Activating Token Index: 796

Text #4

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.7723. Min Act: -0.0000

Data Index: 563342 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.7415. Min Act: -0.0000

Data Index: 1375545 (Python Code)

Max Activating Token Index: 621

Text #6

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1436180 (Python Code)

Max Activating Token Index: 766

Text #7

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.7045. Min Act: -0.0000

Data Index: 1504918 (Python Code)

Max Activating Token Index: 450

Text #8

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1594863 (Python Code)

Max Activating Token Index: 387

Text #9

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1616356 (Python Code)

Max Activating Token Index: 539

Text #10

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1642496 (Python Code)

Max Activating Token Index: 543

Text #11

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1193194 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1525129 (Python Code)

Max Activating Token Index: 940

Text #13

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1552085 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.6688. Min Act: -0.0000

Data Index: 727728 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1485015 (Python Code)

Max Activating Token Index: 120

Text #16

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.6685. Min Act: -0.0000

Data Index: 1151605 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1471531 (Python Code)

Max Activating Token Index: 832

Text #18

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.6134. Min Act: -0.0000

Data Index: 1408268 (Python Code)

Max Activating Token Index: 774

Text #19

Max Range: 1.1554. Min Range: -1.1554

Max Act: 0.6126. Min Act: -0.0000

Data Index: 1452336 (Python Code)

Max Activating Token Index: 678