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

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

Neuron 2429 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: 0.7666. Min Range: -0.7666

Max Act: 0.7666. Min Act: -0.0000

Data Index: 889330 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.7400. Min Act: -0.0000

Data Index: 347268 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1129103 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6987. Min Act: -0.0000

Data Index: 539541 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6939. Min Act: -0.0000

Data Index: 968329 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6412. Min Act: -0.0000

Data Index: 128271 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6295. Min Act: -0.0000

Data Index: 19338 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6341. Min Act: -0.0000

Data Index: 279047 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6781. Min Act: -0.0000

Data Index: 67063 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6262. Min Act: -0.0000

Data Index: 17909 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6540. Min Act: -0.0000

Data Index: 587999 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1141939 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6320. Min Act: -0.0000

Data Index: 710313 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6328. Min Act: -0.0000

Data Index: 348039 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1286476 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6212. Min Act: -0.0000

Data Index: 856480 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.5907. Min Act: -0.0000

Data Index: 618833 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6210. Min Act: -0.0000

Data Index: 178754 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.6610. Min Act: -0.0000

Data Index: 555757 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.7666. Min Range: -0.7666

Max Act: 0.5971. Min Act: -0.0000

Data Index: 77805 (C4 (Web Text))

Max Activating Token Index: 42