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

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

Neuron 3406 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.1274. Min Act: -0.0000

Data Index: 971794 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.1853. Min Act: -0.0000

Data Index: 866597 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0254. Min Act: -0.0000

Data Index: 301737 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.9503. Min Act: -0.0000

Data Index: 843742 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.9255. Min Act: -0.0000

Data Index: 85596 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.9559. Min Act: -0.0000

Data Index: 842321 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 1.1853. Min Range: -1.1853

Max Act: 1.0506. Min Act: -0.0000

Data Index: 1000063 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1345520 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.9006. Min Act: -0.0000

Data Index: 361417 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.9254. Min Act: -0.0000

Data Index: 736499 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.9312. Min Act: -0.0000

Data Index: 594348 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.8415. Min Act: -0.0000

Data Index: 96810 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.8645. Min Act: -0.0000

Data Index: 622003 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.9125. Min Act: -0.0000

Data Index: 1091778 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.8527. Min Act: -0.0000

Data Index: 668068 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.8748. Min Act: -0.0000

Data Index: 789340 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.8941. Min Act: -0.0000

Data Index: 827290 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1253758 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.8030. Min Act: -0.0000

Data Index: 1013948 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 1.1853. Min Range: -1.1853

Max Act: 0.8558. Min Act: -0.0000

Data Index: 32509 (C4 (Web Text))

Max Activating Token Index: 855