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

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

Neuron 2011 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: 2.6090. Min Range: -2.6090

Max Act: 2.6090. Min Act: -0.0000

Data Index: 616540 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.4605. Min Act: -0.0000

Data Index: 458691 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.4186. Min Act: -0.0000

Data Index: 1023423 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.4057. Min Act: -0.0000

Data Index: 1120677 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.2852. Min Act: -0.0000

Data Index: 1154144 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.4605. Min Act: -0.0000

Data Index: 683363 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.3240. Min Act: -0.0000

Data Index: 1223421 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.3074. Min Act: -0.0000

Data Index: 939109 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.4323. Min Act: -0.0000

Data Index: 78805 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.2641. Min Act: -0.0000

Data Index: 290968 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.2819. Min Act: -0.0000

Data Index: 754841 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.2706. Min Act: -0.0000

Data Index: 1084501 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.2653. Min Act: -0.0000

Data Index: 711818 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.2074. Min Act: -0.0000

Data Index: 579106 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.2165. Min Act: -0.0000

Data Index: 1225384 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.1911. Min Act: -0.0000

Data Index: 171385 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.0865. Min Act: -0.0000

Data Index: 1354617 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.2067. Min Act: -0.0000

Data Index: 1165247 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.1839. Min Act: -0.0000

Data Index: 1326427 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 2.6090. Min Range: -2.6090

Max Act: 2.1823. Min Act: -0.0000

Data Index: 186984 (C4 (Web Text))

Max Activating Token Index: 727