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

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

Neuron 238 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0897. Min Act: -0.0003

Data Index: 386096 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0856. Min Act: -0.0003

Data Index: 705246 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0747. Min Act: -0.0003

Data Index: 955121 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0721. Min Act: -0.0004

Data Index: 940421 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0640. Min Act: -0.0003

Data Index: 1196889 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0667. Min Act: -0.0003

Data Index: 1230766 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0639. Min Act: -0.0003

Data Index: 591204 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0657. Min Act: -0.0003

Data Index: 153211 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0629. Min Act: -0.0003

Data Index: 1029323 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0681. Min Act: -0.0003

Data Index: 745898 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1119462 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0645. Min Act: -0.0003

Data Index: 927200 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0647. Min Act: -0.0003

Data Index: 1042900 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1047648 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0634. Min Act: -0.0003

Data Index: 98821 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0628. Min Act: -0.0003

Data Index: 645814 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0625. Min Act: -0.0003

Data Index: 966233 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0600. Min Act: -0.0003

Data Index: 786703 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0620. Min Act: -0.0003

Data Index: 178613 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0572. Min Act: -0.0003

Data Index: 1173632 (C4 (Web Text))

Max Activating Token Index: 172