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

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

Neuron 5739 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: 4.6911. Min Range: -4.6911

Max Act: 4.6911. Min Act: -0.0000

Data Index: 1102796 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.6618. Min Act: -0.0000

Data Index: 492342 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.6095. Min Act: -0.0000

Data Index: 451171 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.4954. Min Act: -0.0000

Data Index: 810544 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.3963. Min Act: -0.0000

Data Index: 943148 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.1947. Min Act: -0.0000

Data Index: 1061328 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.3685. Min Act: -0.0000

Data Index: 915931 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.3902. Min Act: -0.0000

Data Index: 1027939 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.6336. Min Act: -0.0000

Data Index: 1264452 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.2783. Min Act: -0.0000

Data Index: 636947 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.2704. Min Act: -0.0000

Data Index: 40678 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.2532. Min Act: -0.0000

Data Index: 350237 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.2490. Min Act: -0.0000

Data Index: 1249325 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.2145. Min Act: -0.0000

Data Index: 437843 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.0278. Min Act: -0.0000

Data Index: 432387 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.1395. Min Act: -0.0000

Data Index: 640741 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.1413. Min Act: -0.0000

Data Index: 833250 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.0694. Min Act: -0.0000

Data Index: 1023613 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 4.6911. Min Range: -4.6911

Max Act: 4.1128. Min Act: -0.0000

Data Index: 862094 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 4.6911. Min Range: -4.6911

Max Act: 3.9033. Min Act: -0.0000

Data Index: 933539 (C4 (Web Text))

Max Activating Token Index: 159