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

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

Neuron 1716 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1232. Min Range: -1.1232

Max Act: 1.1232. Min Act: -0.0000

Data Index: 756641 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8993. Min Act: -0.0000

Data Index: 895494 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.9106. Min Act: -0.0000

Data Index: 1326395 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.7732. Min Act: -0.0000

Data Index: 21397 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.6090. Min Act: -0.0000

Data Index: 722817 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.6433. Min Act: -0.0000

Data Index: 194239 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.6970. Min Act: -0.0000

Data Index: 810283 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.6975. Min Act: -0.0000

Data Index: 699834 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8224. Min Act: -0.0000

Data Index: 441852 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.6362. Min Act: -0.0000

Data Index: 1195851 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.6141. Min Act: -0.0000

Data Index: 636003 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.6467. Min Act: -0.0000

Data Index: 80879 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.6483. Min Act: -0.0000

Data Index: 440342 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.6048. Min Act: -0.0000

Data Index: 280935 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.6979. Min Act: -0.0000

Data Index: 945422 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1308997 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.5708. Min Act: -0.0000

Data Index: 999451 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.6517. Min Act: -0.0000

Data Index: 1433243 (Python Code)

Max Activating Token Index: 224

Text #18

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1323331 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1189971 (C4 (Web Text))

Max Activating Token Index: 884