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

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

Neuron 3999 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.3432. Min Act: -0.0002

Data Index: 1639854 (Python Code)

Max Activating Token Index: 887

Text #1

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.3800. Min Act: -0.0002

Data Index: 1048380 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.2952. Min Act: -0.0002

Data Index: 533576 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.3250. Min Act: -0.0002

Data Index: 882554 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.3145. Min Act: -0.0002

Data Index: 899329 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.3245. Min Act: -0.0002

Data Index: 979720 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.2786. Min Act: -0.0002

Data Index: 1036831 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.2859. Min Act: -0.0002

Data Index: 687844 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.2781. Min Act: -0.0002

Data Index: 43597 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.2339. Min Act: -0.0002

Data Index: 1173040 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.2608. Min Act: -0.0002

Data Index: 792247 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.2629. Min Act: -0.0002

Data Index: 164212 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.2108. Min Act: -0.0002

Data Index: 719589 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.2300. Min Act: -0.0002

Data Index: 1200986 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.2043. Min Act: -0.0002

Data Index: 625634 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.2242. Min Act: -0.0002

Data Index: 1217368 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.1753. Min Act: -0.0002

Data Index: 1225994 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.1912. Min Act: -0.0002

Data Index: 952637 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.1717. Min Act: -0.0002

Data Index: 1179928 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 1.3800. Min Range: -1.3800

Max Act: 1.1638. Min Act: -0.0002

Data Index: 643792 (C4 (Web Text))

Max Activating Token Index: 137