Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2053 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.3872. Min Range: -5.3872

Max Act: 5.3872. Min Act: -0.0000

Data Index: 888205 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 5.3872. Min Range: -5.3872

Max Act: 4.7802. Min Act: -0.0000

Data Index: 854352 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 5.3872. Min Range: -5.3872

Max Act: 4.7212. Min Act: -0.0000

Data Index: 442919 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 5.3872. Min Range: -5.3872

Max Act: 4.5324. Min Act: -0.0000

Data Index: 585637 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 5.3872. Min Range: -5.3872

Max Act: 4.2831. Min Act: -0.0000

Data Index: 324811 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 5.3872. Min Range: -5.3872

Max Act: 4.0765. Min Act: -0.0000

Data Index: 1168468 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 5.3872. Min Range: -5.3872

Max Act: 4.1068. Min Act: -0.0000

Data Index: 876738 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 5.3872. Min Range: -5.3872

Max Act: 3.9874. Min Act: -0.0000

Data Index: 593374 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 5.3872. Min Range: -5.3872

Max Act: 3.9860. Min Act: -0.0000

Data Index: 225202 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 5.3872. Min Range: -5.3872

Max Act: 3.9748. Min Act: -0.0000

Data Index: 491167 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 5.3872. Min Range: -5.3872

Max Act: 4.2936. Min Act: -0.0000

Data Index: 744345 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 5.3872. Min Range: -5.3872

Max Act: 4.0913. Min Act: -0.0000

Data Index: 320897 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 5.3872. Min Range: -5.3872

Max Act: 3.7851. Min Act: -0.0000

Data Index: 973241 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 5.3872. Min Range: -5.3872

Max Act: 3.9187. Min Act: -0.0000

Data Index: 1054495 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 5.3872. Min Range: -5.3872

Max Act: 3.8824. Min Act: -0.0000

Data Index: 8690 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 5.3872. Min Range: -5.3872

Max Act: 3.7205. Min Act: -0.0000

Data Index: 1333262 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 5.3872. Min Range: -5.3872

Max Act: 3.7943. Min Act: -0.0000

Data Index: 859823 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 5.3872. Min Range: -5.3872

Max Act: 3.9392. Min Act: -0.0000

Data Index: 1097737 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 5.3872. Min Range: -5.3872

Max Act: 3.5946. Min Act: -0.0000

Data Index: 393078 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 5.3872. Min Range: -5.3872

Max Act: 3.7430. Min Act: -0.0000

Data Index: 1342347 (C4 (Web Text))

Max Activating Token Index: 815