Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 906 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1774. Min Range: -1.1774

Max Act: 1.0890. Min Act: -0.0000

Data Index: 134086 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 1.1774. Min Range: -1.1774

Max Act: 1.1774. Min Act: -0.0000

Data Index: 1071947 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 1.1774. Min Range: -1.1774

Max Act: 1.1049. Min Act: -0.0000

Data Index: 355796 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 1.1774. Min Range: -1.1774

Max Act: 1.1603. Min Act: -0.0000

Data Index: 899543 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 1.1774. Min Range: -1.1774

Max Act: 1.0812. Min Act: -0.0000

Data Index: 223169 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 1.1774. Min Range: -1.1774

Max Act: 1.0129. Min Act: -0.0000

Data Index: 168324 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 1.1774. Min Range: -1.1774

Max Act: 1.0665. Min Act: -0.0000

Data Index: 1015911 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 1.1774. Min Range: -1.1774

Max Act: 1.0666. Min Act: -0.0000

Data Index: 1348698 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9822. Min Act: -0.0000

Data Index: 502736 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1580290 (Python Code)

Max Activating Token Index: 207

Text #10

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9465. Min Act: -0.0000

Data Index: 1502456 (Python Code)

Max Activating Token Index: 246

Text #11

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1590100 (Python Code)

Max Activating Token Index: 637

Text #12

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9160. Min Act: -0.0000

Data Index: 496909 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9186. Min Act: -0.0000

Data Index: 587734 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9217. Min Act: -0.0000

Data Index: 794625 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1584882 (Python Code)

Max Activating Token Index: 66

Text #16

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8656. Min Act: -0.0000

Data Index: 85655 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.9055. Min Act: -0.0000

Data Index: 182629 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8569. Min Act: -0.0000

Data Index: 324670 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 1.1774. Min Range: -1.1774

Max Act: 0.8980. Min Act: -0.0000

Data Index: 171109 (C4 (Web Text))

Max Activating Token Index: 894