Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 626 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.2193. Min Act: -0.0001

Data Index: 117481 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.2189. Min Act: -0.0001

Data Index: 3918 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.2122. Min Act: -0.0001

Data Index: 308862 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.2019. Min Act: -0.0002

Data Index: 1129992 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.2027. Min Act: -0.0002

Data Index: 943248 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.2016. Min Act: -0.0001

Data Index: 485086 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1854. Min Act: -0.0001

Data Index: 1140985 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1833. Min Act: -0.0001

Data Index: 843956 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1963. Min Act: -0.0001

Data Index: 592440 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1923. Min Act: -0.0001

Data Index: 1313813 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1766. Min Act: -0.0001

Data Index: 557879 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1765. Min Act: -0.0001

Data Index: 161545 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1797. Min Act: -0.0001

Data Index: 1159237 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1775. Min Act: -0.0001

Data Index: 718688 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1712. Min Act: -0.0001

Data Index: 177799 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1651. Min Act: -0.0001

Data Index: 807502 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1755. Min Act: -0.0002

Data Index: 1294015 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1620. Min Act: -0.0001

Data Index: 1056382 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1702. Min Act: -0.0001

Data Index: 513818 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.2193. Min Range: -0.2193

Max Act: 0.1732. Min Act: -0.0001

Data Index: 136494 (C4 (Web Text))

Max Activating Token Index: 233