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

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

Neuron 333 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: 0.9012. Min Range: -0.9012

Max Act: 0.9012. Min Act: -0.0000

Data Index: 250746 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.8679. Min Act: -0.0000

Data Index: 959276 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.8429. Min Act: -0.0000

Data Index: 1508422 (Python Code)

Max Activating Token Index: 880

Text #3

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.8342. Min Act: -0.0000

Data Index: 1432556 (Python Code)

Max Activating Token Index: 930

Text #4

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.6968. Min Act: -0.0000

Data Index: 1454826 (Python Code)

Max Activating Token Index: 273

Text #5

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1648878 (Python Code)

Max Activating Token Index: 895

Text #6

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7513. Min Act: -0.0000

Data Index: 920887 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.8112. Min Act: -0.0000

Data Index: 172114 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1558813 (Python Code)

Max Activating Token Index: 708

Text #9

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7059. Min Act: -0.0000

Data Index: 1558081 (Python Code)

Max Activating Token Index: 900

Text #10

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1400009 (Python Code)

Max Activating Token Index: 473

Text #11

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7423. Min Act: -0.0000

Data Index: 1458197 (Python Code)

Max Activating Token Index: 698

Text #12

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1536794 (Python Code)

Max Activating Token Index: 565

Text #13

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.6966. Min Act: -0.0000

Data Index: 506754 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.6774. Min Act: -0.0000

Data Index: 1636055 (Python Code)

Max Activating Token Index: 328

Text #15

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1465178 (Python Code)

Max Activating Token Index: 289

Text #16

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7279. Min Act: -0.0000

Data Index: 373981 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.7207. Min Act: -0.0000

Data Index: 533679 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1656248 (Python Code)

Max Activating Token Index: 554

Text #19

Max Range: 0.9012. Min Range: -0.9012

Max Act: 0.6475. Min Act: -0.0000

Data Index: 877830 (C4 (Web Text))

Max Activating Token Index: 340