Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1991 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5042. Min Act: -0.0004

Data Index: 1089505 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5798. Min Act: -0.0004

Data Index: 1216234 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5615. Min Act: -0.0004

Data Index: 1169897 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5586. Min Act: -0.0004

Data Index: 730258 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5397. Min Act: -0.0004

Data Index: 350686 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5872. Min Act: -0.0004

Data Index: 618201 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5682. Min Act: -0.0004

Data Index: 1319415 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5455. Min Act: -0.0004

Data Index: 628783 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5644. Min Act: -0.0004

Data Index: 1105422 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5444. Min Act: -0.0004

Data Index: 1084227 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.4643. Min Act: -0.0004

Data Index: 422925 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5407. Min Act: -0.0004

Data Index: 1242082 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.6141. Min Act: -0.0004

Data Index: 735895 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5759. Min Act: -0.0004

Data Index: 1205725 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5060. Min Act: -0.0004

Data Index: 1240175 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.4723. Min Act: -0.0004

Data Index: 545746 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.6111. Min Act: -0.0004

Data Index: 1181031 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5729. Min Act: -0.0004

Data Index: 205156 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5530. Min Act: -0.0004

Data Index: 38818 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 0.6141. Min Range: -0.6141

Max Act: 0.5509. Min Act: -0.0004

Data Index: 718999 (C4 (Web Text))

Max Activating Token Index: 496