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

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

Neuron 3269 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1049728 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0684. Min Act: -0.0001

Data Index: 376763 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0720. Min Act: -0.0001

Data Index: 1089684 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0667. Min Act: -0.0001

Data Index: 272954 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0643. Min Act: -0.0001

Data Index: 412362 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0615. Min Act: -0.0001

Data Index: 74321 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0638. Min Act: -0.0001

Data Index: 619520 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1260857 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0546. Min Act: -0.0001

Data Index: 1079680 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0580. Min Act: -0.0001

Data Index: 620040 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0598. Min Act: -0.0001

Data Index: 342997 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0583. Min Act: -0.0001

Data Index: 391532 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0492. Min Act: -0.0001

Data Index: 1177786 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0507. Min Act: -0.0001

Data Index: 219697 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0557. Min Act: -0.0001

Data Index: 569437 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0490. Min Act: -0.0001

Data Index: 1322529 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0513. Min Act: -0.0001

Data Index: 214155 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0533. Min Act: -0.0001

Data Index: 769463 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0454. Min Act: -0.0001

Data Index: 277632 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0467. Min Act: -0.0001

Data Index: 437291 (C4 (Web Text))

Max Activating Token Index: 555