Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1350 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.3814. Min Range: -8.3814

Max Act: 8.3814. Min Act: -0.0001

Data Index: 147576 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 8.3814. Min Range: -8.3814

Max Act: 7.7275. Min Act: -0.0001

Data Index: 384231 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 8.3814. Min Range: -8.3814

Max Act: 8.1069. Min Act: -0.0001

Data Index: 1263071 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 8.3814. Min Range: -8.3814

Max Act: 8.2566. Min Act: -0.0001

Data Index: 1270650 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 8.3814. Min Range: -8.3814

Max Act: 7.8126. Min Act: -0.0001

Data Index: 1029668 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 8.3814. Min Range: -8.3814

Max Act: 7.7085. Min Act: -0.0001

Data Index: 561086 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 8.3814. Min Range: -8.3814

Max Act: 8.1445. Min Act: -0.0001

Data Index: 1339961 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 8.3814. Min Range: -8.3814

Max Act: 7.7648. Min Act: -0.0001

Data Index: 263597 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 8.3814. Min Range: -8.3814

Max Act: 7.6762. Min Act: -0.0001

Data Index: 49841 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 8.3814. Min Range: -8.3814

Max Act: 7.1475. Min Act: -0.0001

Data Index: 365749 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 8.3814. Min Range: -8.3814

Max Act: 7.2586. Min Act: -0.0001

Data Index: 191227 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 8.3814. Min Range: -8.3814

Max Act: 6.9554. Min Act: -0.0001

Data Index: 754433 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 8.3814. Min Range: -8.3814

Max Act: 7.4573. Min Act: -0.0001

Data Index: 1286953 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 8.3814. Min Range: -8.3814

Max Act: 7.2826. Min Act: -0.0001

Data Index: 1043526 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 8.3814. Min Range: -8.3814

Max Act: 6.5357. Min Act: -0.0001

Data Index: 946034 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 8.3814. Min Range: -8.3814

Max Act: 6.6343. Min Act: -0.0001

Data Index: 1310332 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 8.3814. Min Range: -8.3814

Max Act: 6.4220. Min Act: -0.0001

Data Index: 254126 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 8.3814. Min Range: -8.3814

Max Act: 6.3719. Min Act: -0.0001

Data Index: 592880 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 8.3814. Min Range: -8.3814

Max Act: 6.4486. Min Act: -0.0001

Data Index: 169773 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 8.3814. Min Range: -8.3814

Max Act: 6.2196. Min Act: -0.0001

Data Index: 771289 (C4 (Web Text))

Max Activating Token Index: 753