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

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

Neuron 3557 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7767. Min Act: -0.0000

Data Index: 461796 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7733. Min Act: -0.0000

Data Index: 310426 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5949. Min Act: -0.0000

Data Index: 661527 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6133. Min Act: -0.0000

Data Index: 110763 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5780. Min Act: -0.0000

Data Index: 166839 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5817. Min Act: -0.0000

Data Index: 792844 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1297929 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5394. Min Act: -0.0000

Data Index: 696669 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5496. Min Act: -0.0000

Data Index: 88301 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5300. Min Act: -0.0000

Data Index: 736791 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.4922. Min Act: -0.0000

Data Index: 988241 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.4806. Min Act: -0.0000

Data Index: 524334 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5258. Min Act: -0.0000

Data Index: 257344 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1525231 (Python Code)

Max Activating Token Index: 608

Text #14

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5006. Min Act: -0.0000

Data Index: 689774 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1180135 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.4586. Min Act: -0.0000

Data Index: 772032 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1083926 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.4388. Min Act: -0.0000

Data Index: 288698 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.4185. Min Act: -0.0000

Data Index: 799188 (C4 (Web Text))

Max Activating Token Index: 649