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

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

Neuron 3293 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1384349 (Python Code)

Max Activating Token Index: 234

Text #1

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1127. Min Act: -0.0000

Data Index: 1470710 (Python Code)

Max Activating Token Index: 225

Text #2

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1574337 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1140273 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1556350 (Python Code)

Max Activating Token Index: 679

Text #5

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1576688 (Python Code)

Max Activating Token Index: 413

Text #6

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1009. Min Act: -0.0000

Data Index: 589024 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0880. Min Act: -0.0000

Data Index: 1412996 (Python Code)

Max Activating Token Index: 457

Text #8

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1538423 (Python Code)

Max Activating Token Index: 383

Text #9

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0837. Min Act: -0.0000

Data Index: 501312 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1645596 (Python Code)

Max Activating Token Index: 997

Text #11

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0776. Min Act: -0.0000

Data Index: 1475831 (Python Code)

Max Activating Token Index: 620

Text #12

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1542525 (Python Code)

Max Activating Token Index: 86

Text #13

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0817. Min Act: -0.0000

Data Index: 1637651 (Python Code)

Max Activating Token Index: 423

Text #14

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0823. Min Act: -0.0000

Data Index: 1370411 (Python Code)

Max Activating Token Index: 790

Text #15

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0775. Min Act: -0.0000

Data Index: 423973 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0711. Min Act: -0.0000

Data Index: 1400909 (Python Code)

Max Activating Token Index: 349

Text #17

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0706. Min Act: -0.0000

Data Index: 1147568 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0784. Min Act: -0.0000

Data Index: 370360 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0677. Min Act: -0.0000

Data Index: 1065491 (C4 (Web Text))

Max Activating Token Index: 22