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

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

Neuron 1208 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4430. Min Range: -4.4430

Max Act: 4.4430. Min Act: -0.0000

Data Index: 1511259 (Python Code)

Max Activating Token Index: 458

Text #1

Max Range: 4.4430. Min Range: -4.4430

Max Act: 3.2864. Min Act: -0.0000

Data Index: 328083 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 4.4430. Min Range: -4.4430

Max Act: 3.6229. Min Act: -0.0000

Data Index: 1184195 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 4.4430. Min Range: -4.4430

Max Act: 2.8233. Min Act: -0.0000

Data Index: 656671 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 4.4430. Min Range: -4.4430

Max Act: 2.8510. Min Act: -0.0000

Data Index: 1065360 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 4.4430. Min Range: -4.4430

Max Act: 3.0796. Min Act: -0.0000

Data Index: 353519 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 4.4430. Min Range: -4.4430

Max Act: 3.1948. Min Act: -0.0000

Data Index: 1413836 (Python Code)

Max Activating Token Index: 986

Text #7

Max Range: 4.4430. Min Range: -4.4430

Max Act: 2.5473. Min Act: -0.0000

Data Index: 1198396 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 4.4430. Min Range: -4.4430

Max Act: 2.2853. Min Act: -0.0000

Data Index: 1362245 (Python Code)

Max Activating Token Index: 801

Text #9

Max Range: 4.4430. Min Range: -4.4430

Max Act: 2.0153. Min Act: -0.0000

Data Index: 27766 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 4.4430. Min Range: -4.4430

Max Act: 1.8861. Min Act: -0.0000

Data Index: 1444714 (Python Code)

Max Activating Token Index: 365

Text #11

Max Range: 4.4430. Min Range: -4.4430

Max Act: 2.1606. Min Act: -0.0000

Data Index: 903593 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 4.4430. Min Range: -4.4430

Max Act: 2.0845. Min Act: -0.0000

Data Index: 1546410 (Python Code)

Max Activating Token Index: 37

Text #13

Max Range: 4.4430. Min Range: -4.4430

Max Act: 1.9513. Min Act: -0.0000

Data Index: 797635 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 4.4430. Min Range: -4.4430

Max Act: 1.8327. Min Act: -0.0000

Data Index: 792013 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 4.4430. Min Range: -4.4430

Max Act: 1.8362. Min Act: -0.0000

Data Index: 924357 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 4.4430. Min Range: -4.4430

Max Act: 1.7980. Min Act: -0.0000

Data Index: 1586671 (Python Code)

Max Activating Token Index: 811

Text #17

Max Range: 4.4430. Min Range: -4.4430

Max Act: 1.5585. Min Act: -0.0000

Data Index: 639330 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 4.4430. Min Range: -4.4430

Max Act: 1.6292. Min Act: -0.0000

Data Index: 1515112 (Python Code)

Max Activating Token Index: 344

Text #19

Max Range: 4.4430. Min Range: -4.4430

Max Act: 1.6586. Min Act: -0.0000

Data Index: 1368406 (Python Code)

Max Activating Token Index: 636