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

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

Neuron 3344 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1129356 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1061284 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0155. Min Act: -0.0002

Data Index: 463287 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0149. Min Act: -0.0002

Data Index: 705525 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0148. Min Act: -0.0002

Data Index: 50820 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0146. Min Act: -0.0002

Data Index: 661533 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0146. Min Act: -0.0002

Data Index: 576829 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0146. Min Act: -0.0002

Data Index: 842676 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0148. Min Act: -0.0002

Data Index: 540577 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1576665 (Python Code)

Max Activating Token Index: 146

Text #10

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1031490 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0145. Min Act: -0.0002

Data Index: 625384 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0145. Min Act: -0.0002

Data Index: 136837 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0144. Min Act: -0.0002

Data Index: 688888 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0145. Min Act: -0.0002

Data Index: 855399 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0145. Min Act: -0.0002

Data Index: 622756 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0145. Min Act: -0.0002

Data Index: 309061 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0144. Min Act: -0.0002

Data Index: 937848 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1048248 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0144. Min Act: -0.0002

Data Index: 911842 (C4 (Web Text))

Max Activating Token Index: 664