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

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

Neuron 3907 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.8613. Min Act: -0.0001

Data Index: 1615611 (Python Code)

Max Activating Token Index: 236

Text #1

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7454. Min Act: -0.0001

Data Index: 1389852 (Python Code)

Max Activating Token Index: 714

Text #2

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7959. Min Act: -0.0001

Data Index: 1396282 (Python Code)

Max Activating Token Index: 622

Text #3

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1628102 (Python Code)

Max Activating Token Index: 319

Text #4

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7026. Min Act: -0.0001

Data Index: 1623937 (Python Code)

Max Activating Token Index: 589

Text #5

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7363. Min Act: -0.0001

Data Index: 1573420 (Python Code)

Max Activating Token Index: 259

Text #6

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7649. Min Act: -0.0001

Data Index: 1569494 (Python Code)

Max Activating Token Index: 664

Text #7

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7526. Min Act: -0.0000

Data Index: 1475814 (Python Code)

Max Activating Token Index: 730

Text #8

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7064. Min Act: -0.0001

Data Index: 1461021 (Python Code)

Max Activating Token Index: 337

Text #9

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6486. Min Act: -0.0001

Data Index: 1585254 (Python Code)

Max Activating Token Index: 283

Text #10

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6779. Min Act: -0.0001

Data Index: 1570712 (Python Code)

Max Activating Token Index: 739

Text #11

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6310. Min Act: -0.0001

Data Index: 1432296 (Python Code)

Max Activating Token Index: 95

Text #12

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6404. Min Act: -0.0001

Data Index: 1449641 (Python Code)

Max Activating Token Index: 763

Text #13

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6170. Min Act: -0.0000

Data Index: 1410657 (Python Code)

Max Activating Token Index: 195

Text #14

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6448. Min Act: -0.0001

Data Index: 1439359 (Python Code)

Max Activating Token Index: 927

Text #15

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6394. Min Act: -0.0001

Data Index: 1365765 (Python Code)

Max Activating Token Index: 151

Text #16

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1389546 (Python Code)

Max Activating Token Index: 399

Text #17

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1535210 (Python Code)

Max Activating Token Index: 366

Text #18

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1602756 (Python Code)

Max Activating Token Index: 110

Text #19

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.5772. Min Act: -0.0001

Data Index: 1580152 (Python Code)

Max Activating Token Index: 112