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

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

Neuron 3645 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.8901. Min Act: -0.0000

Data Index: 400991 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.9185. Min Act: -0.0000

Data Index: 447033 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.6904. Min Act: -0.0000

Data Index: 1089209 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.6941. Min Act: -0.0000

Data Index: 978957 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.6740. Min Act: -0.0000

Data Index: 33530 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.7426. Min Act: -0.0000

Data Index: 16183 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.8507. Min Act: -0.0000

Data Index: 403028 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.6245. Min Act: -0.0000

Data Index: 773447 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.6377. Min Act: -0.0000

Data Index: 854314 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.6147. Min Act: -0.0000

Data Index: 1359519 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.6495. Min Act: -0.0000

Data Index: 1133943 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.5594. Min Act: -0.0000

Data Index: 474113 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.4494. Min Act: -0.0000

Data Index: 1525978 (Python Code)

Max Activating Token Index: 592

Text #13

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.5315. Min Act: -0.0000

Data Index: 425866 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.5242. Min Act: -0.0000

Data Index: 351135 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.5127. Min Act: -0.0000

Data Index: 1112433 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.5146. Min Act: -0.0000

Data Index: 685201 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.4915. Min Act: -0.0000

Data Index: 578166 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.5734. Min Act: -0.0000

Data Index: 1265932 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 1.9185. Min Range: -1.9185

Max Act: 1.5631. Min Act: -0.0000

Data Index: 66938 (C4 (Web Text))

Max Activating Token Index: 287