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

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

Neuron 4505 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: 1.5038. Min Range: -1.5038

Max Act: 1.5038. Min Act: -0.0000

Data Index: 592492 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.1801. Min Act: -0.0000

Data Index: 884149 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.2393. Min Act: -0.0000

Data Index: 1001753 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.1870. Min Act: -0.0000

Data Index: 975903 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1038096 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.2202. Min Act: -0.0000

Data Index: 261907 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.2335. Min Act: -0.0000

Data Index: 1243173 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.0495. Min Act: -0.0000

Data Index: 733462 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.0411. Min Act: -0.0000

Data Index: 183833 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.1061. Min Act: -0.0000

Data Index: 992705 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.1743. Min Act: -0.0000

Data Index: 1266686 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.0498. Min Act: -0.0000

Data Index: 955806 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.0955. Min Act: -0.0000

Data Index: 851180 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 1.5038. Min Range: -1.5038

Max Act: 0.9667. Min Act: -0.0000

Data Index: 897617 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.0240. Min Act: -0.0000

Data Index: 476807 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.0825. Min Act: -0.0000

Data Index: 1177186 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.0094. Min Act: -0.0000

Data Index: 1205803 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.0047. Min Act: -0.0000

Data Index: 1129414 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 1.5038. Min Range: -1.5038

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1338737 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 1.5038. Min Range: -1.5038

Max Act: 0.9663. Min Act: -0.0000

Data Index: 1272917 (C4 (Web Text))

Max Activating Token Index: 335