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

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

Neuron 5428 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.9551. Min Act: -0.0000

Data Index: 1559102 (Python Code)

Max Activating Token Index: 895

Text #1

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.9760. Min Act: -0.0000

Data Index: 1539297 (Python Code)

Max Activating Token Index: 426

Text #2

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.9296. Min Act: -0.0000

Data Index: 1436737 (Python Code)

Max Activating Token Index: 641

Text #3

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.8413. Min Act: -0.0000

Data Index: 1538711 (Python Code)

Max Activating Token Index: 753

Text #4

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.7203. Min Act: -0.0000

Data Index: 1636989 (Python Code)

Max Activating Token Index: 607

Text #5

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.8270. Min Act: -0.0000

Data Index: 1060416 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.9360. Min Act: -0.0000

Data Index: 457004 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.8970. Min Act: -0.0000

Data Index: 1630072 (Python Code)

Max Activating Token Index: 909

Text #8

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.6242. Min Act: -0.0000

Data Index: 1106994 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.8318. Min Act: -0.0000

Data Index: 424820 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.7964. Min Act: -0.0000

Data Index: 113323 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.6991. Min Act: -0.0000

Data Index: 802175 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.7874. Min Act: -0.0000

Data Index: 1527736 (Python Code)

Max Activating Token Index: 649

Text #13

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.8378. Min Act: -0.0000

Data Index: 1101918 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.7037. Min Act: -0.0000

Data Index: 513871 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.7168. Min Act: -0.0000

Data Index: 1162530 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.6751. Min Act: -0.0000

Data Index: 1404228 (Python Code)

Max Activating Token Index: 258

Text #17

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.6597. Min Act: -0.0000

Data Index: 1389716 (Python Code)

Max Activating Token Index: 900

Text #18

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.6582. Min Act: -0.0000

Data Index: 1566155 (Python Code)

Max Activating Token Index: 174

Text #19

Max Range: 1.9760. Min Range: -1.9760

Max Act: 1.6541. Min Act: -0.0000

Data Index: 185656 (C4 (Web Text))

Max Activating Token Index: 730