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

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

Neuron 3761 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: 0.2806. Min Range: -0.2806

Max Act: 0.2796. Min Act: -0.0000

Data Index: 517564 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2806. Min Act: -0.0000

Data Index: 547703 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2661. Min Act: -0.0001

Data Index: 666980 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2571. Min Act: -0.0001

Data Index: 694360 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2639. Min Act: -0.0000

Data Index: 1132472 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2477. Min Act: -0.0001

Data Index: 1296500 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2464. Min Act: -0.0000

Data Index: 140669 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2317. Min Act: -0.0000

Data Index: 932644 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2204. Min Act: -0.0000

Data Index: 994699 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1105800 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1351891 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.1997. Min Act: -0.0000

Data Index: 1313245 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1249049 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.1908. Min Act: -0.0000

Data Index: 2507 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.1882. Min Act: -0.0000

Data Index: 726300 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.1845. Min Act: -0.0000

Data Index: 305274 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.1870. Min Act: -0.0000

Data Index: 949595 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.1812. Min Act: -0.0000

Data Index: 387283 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.1740. Min Act: -0.0000

Data Index: 218975 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.2806. Min Range: -0.2806

Max Act: 0.1788. Min Act: -0.0000

Data Index: 958676 (C4 (Web Text))

Max Activating Token Index: 186