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

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

Neuron 5539 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1371. Min Act: -0.0000

Data Index: 681497 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0835. Min Act: -0.0000

Data Index: 454637 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0760. Min Act: -0.0000

Data Index: 307857 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0752. Min Act: -0.0000

Data Index: 720654 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0636. Min Act: -0.0000

Data Index: 556039 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0686. Min Act: -0.0000

Data Index: 214442 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0812. Min Act: -0.0000

Data Index: 587377 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0654. Min Act: -0.0000

Data Index: 1328372 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0670. Min Act: -0.0000

Data Index: 309093 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0681. Min Act: -0.0000

Data Index: 971392 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1057213 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0635. Min Act: -0.0000

Data Index: 845749 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0523. Min Act: -0.0000

Data Index: 39171 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0636. Min Act: -0.0000

Data Index: 361335 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1402916 (Python Code)

Max Activating Token Index: 285

Text #15

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0525. Min Act: -0.0000

Data Index: 677627 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0474. Min Act: -0.0000

Data Index: 1086172 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0431. Min Act: -0.0000

Data Index: 1343386 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0525. Min Act: -0.0000

Data Index: 932562 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0553. Min Act: -0.0000

Data Index: 50378 (C4 (Web Text))

Max Activating Token Index: 662