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

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

Neuron 2778 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7446. Min Range: -7.7446

Max Act: 7.7446. Min Act: -0.0000

Data Index: 421310 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 7.7446. Min Range: -7.7446

Max Act: 7.5043. Min Act: -0.0000

Data Index: 517962 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 7.7446. Min Range: -7.7446

Max Act: 6.5648. Min Act: -0.0000

Data Index: 344115 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 7.7446. Min Range: -7.7446

Max Act: 6.6027. Min Act: -0.0000

Data Index: 257519 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 7.7446. Min Range: -7.7446

Max Act: 5.8067. Min Act: -0.0000

Data Index: 1273905 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 7.7446. Min Range: -7.7446

Max Act: 5.4184. Min Act: -0.0000

Data Index: 875849 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 7.7446. Min Range: -7.7446

Max Act: 5.5159. Min Act: -0.0000

Data Index: 80097 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 7.7446. Min Range: -7.7446

Max Act: 5.1038. Min Act: -0.0000

Data Index: 410186 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 7.7446. Min Range: -7.7446

Max Act: 5.0016. Min Act: -0.0000

Data Index: 1022502 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 7.7446. Min Range: -7.7446

Max Act: 4.7164. Min Act: -0.0000

Data Index: 875926 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 7.7446. Min Range: -7.7446

Max Act: 4.1773. Min Act: -0.0000

Data Index: 1058936 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 7.7446. Min Range: -7.7446

Max Act: 3.9722. Min Act: -0.0000

Data Index: 1043030 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 7.7446. Min Range: -7.7446

Max Act: 3.4443. Min Act: -0.0000

Data Index: 908149 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 7.7446. Min Range: -7.7446

Max Act: 2.7988. Min Act: -0.0000

Data Index: 900071 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 7.7446. Min Range: -7.7446

Max Act: 3.4504. Min Act: -0.0000

Data Index: 104189 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 7.7446. Min Range: -7.7446

Max Act: 3.2284. Min Act: -0.0000

Data Index: 205208 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 7.7446. Min Range: -7.7446

Max Act: 3.3343. Min Act: -0.0000

Data Index: 842163 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 7.7446. Min Range: -7.7446

Max Act: 2.6959. Min Act: -0.0000

Data Index: 764502 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 7.7446. Min Range: -7.7446

Max Act: 1.9383. Min Act: -0.0000

Data Index: 1021490 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 7.7446. Min Range: -7.7446

Max Act: 2.6951. Min Act: -0.0000

Data Index: 1230485 (C4 (Web Text))

Max Activating Token Index: 91