Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2102 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.7154. Min Act: -0.0003

Data Index: 1298522 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.6635. Min Act: -0.0003

Data Index: 300797 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.6171. Min Act: -0.0003

Data Index: 810655 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5481. Min Act: -0.0003

Data Index: 299318 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5266. Min Act: -0.0003

Data Index: 1155199 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5067. Min Act: -0.0003

Data Index: 1225309 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5156. Min Act: -0.0003

Data Index: 468648 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5193. Min Act: -0.0003

Data Index: 40583 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5015. Min Act: -0.0003

Data Index: 119374 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4993. Min Act: -0.0003

Data Index: 330673 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4905. Min Act: -0.0003

Data Index: 722271 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4859. Min Act: -0.0003

Data Index: 488830 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4506. Min Act: -0.0002

Data Index: 241474 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4642. Min Act: -0.0003

Data Index: 826520 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4553. Min Act: -0.0003

Data Index: 813201 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4376. Min Act: -0.0003

Data Index: 527452 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4639. Min Act: -0.0003

Data Index: 827690 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4448. Min Act: -0.0003

Data Index: 1265959 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4573. Min Act: -0.0003

Data Index: 620425 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4566. Min Act: -0.0003

Data Index: 865982 (C4 (Web Text))

Max Activating Token Index: 172