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

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

Neuron 818 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 15.9405. Min Range: -15.9405

Max Act: 15.9405. Min Act: -0.0000

Data Index: 443396 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 15.9405. Min Range: -15.9405

Max Act: 15.6128. Min Act: -0.0000

Data Index: 812985 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 15.9405. Min Range: -15.9405

Max Act: 15.1521. Min Act: -0.0000

Data Index: 55729 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 15.9405. Min Range: -15.9405

Max Act: 15.2867. Min Act: -0.0000

Data Index: 123127 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 15.9405. Min Range: -15.9405

Max Act: 15.2849. Min Act: -0.0000

Data Index: 278514 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 15.9405. Min Range: -15.9405

Max Act: 15.2881. Min Act: -0.0000

Data Index: 45930 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 15.9405. Min Range: -15.9405

Max Act: 15.1527. Min Act: -0.0000

Data Index: 433615 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 15.9405. Min Range: -15.9405

Max Act: 15.2201. Min Act: -0.0000

Data Index: 1030818 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 15.9405. Min Range: -15.9405

Max Act: 15.0201. Min Act: -0.0000

Data Index: 609563 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 15.9405. Min Range: -15.9405

Max Act: 14.9474. Min Act: -0.0000

Data Index: 875289 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 15.9405. Min Range: -15.9405

Max Act: 15.0164. Min Act: -0.0000

Data Index: 177251 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 15.9405. Min Range: -15.9405

Max Act: 15.0169. Min Act: -0.0000

Data Index: 1254723 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 15.9405. Min Range: -15.9405

Max Act: 14.9515. Min Act: -0.0000

Data Index: 378408 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 15.9405. Min Range: -15.9405

Max Act: 14.7379. Min Act: -0.0000

Data Index: 964380 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 15.9405. Min Range: -15.9405

Max Act: 14.6033. Min Act: -0.0000

Data Index: 490401 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 15.9405. Min Range: -15.9405

Max Act: 14.6017. Min Act: -0.0000

Data Index: 860283 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 15.9405. Min Range: -15.9405

Max Act: 14.6729. Min Act: -0.0000

Data Index: 432447 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 15.9405. Min Range: -15.9405

Max Act: 10.1557. Min Act: -0.0000

Data Index: 312807 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 15.9405. Min Range: -15.9405

Max Act: 8.9724. Min Act: -0.0000

Data Index: 200169 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 15.9405. Min Range: -15.9405

Max Act: 7.8831. Min Act: -0.0000

Data Index: 1266480 (C4 (Web Text))

Max Activating Token Index: 100