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

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

Neuron 3448 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: 0.3837. Min Range: -0.3837

Max Act: 0.3529. Min Act: -0.0000

Data Index: 568409 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3105. Min Act: -0.0000

Data Index: 635502 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.3837. Min Act: -0.0000

Data Index: 612226 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2820. Min Act: -0.0000

Data Index: 882627 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2884. Min Act: -0.0000

Data Index: 19257 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1058960 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2834. Min Act: -0.0000

Data Index: 935683 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2880. Min Act: -0.0000

Data Index: 142278 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2636. Min Act: -0.0000

Data Index: 527016 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2659. Min Act: -0.0000

Data Index: 241395 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1342784 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1343371 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1324366 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2178. Min Act: -0.0000

Data Index: 684696 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2340. Min Act: -0.0000

Data Index: 401215 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2185. Min Act: -0.0000

Data Index: 426699 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2254. Min Act: -0.0000

Data Index: 1018039 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2140. Min Act: -0.0000

Data Index: 878945 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2192. Min Act: -0.0000

Data Index: 39912 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.3837. Min Range: -0.3837

Max Act: 0.2245. Min Act: -0.0000

Data Index: 971057 (C4 (Web Text))

Max Activating Token Index: 378