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

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

Neuron 3688 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.9284. Min Act: -0.0000

Data Index: 494928 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.5922. Min Act: 0.0000

Data Index: 452729 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.5110. Min Act: -0.0000

Data Index: 1038253 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.6757. Min Act: -0.0000

Data Index: 127717 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.5979. Min Act: -0.0000

Data Index: 1152283 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.3368. Min Act: -0.0000

Data Index: 375952 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.4892. Min Act: -0.0000

Data Index: 663851 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 2.9284. Min Range: -2.9284

Max Act: 1.9945. Min Act: -0.0000

Data Index: 727560 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.3326. Min Act: -0.0000

Data Index: 227685 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.2021. Min Act: -0.0000

Data Index: 1056898 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.1918. Min Act: -0.0000

Data Index: 822627 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.3287. Min Act: -0.0000

Data Index: 1236725 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.5293. Min Act: -0.0000

Data Index: 1339048 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.3365. Min Act: -0.0000

Data Index: 306501 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.1794. Min Act: -0.0000

Data Index: 1202778 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.1466. Min Act: -0.0000

Data Index: 1144856 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.2349. Min Act: -0.0000

Data Index: 780689 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.0813. Min Act: -0.0000

Data Index: 789994 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.0412. Min Act: -0.0000

Data Index: 965455 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 2.9284. Min Range: -2.9284

Max Act: 2.0189. Min Act: -0.0000

Data Index: 863661 (C4 (Web Text))

Max Activating Token Index: 871