Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3504 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.9710. Min Act: -0.0000

Data Index: 107561 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6981. Min Act: -0.0000

Data Index: 466565 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6639. Min Act: -0.0000

Data Index: 1303854 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.5686. Min Act: -0.0000

Data Index: 89573 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6055. Min Act: -0.0000

Data Index: 177317 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1099680 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6037. Min Act: -0.0000

Data Index: 1216253 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.5934. Min Act: -0.0000

Data Index: 360799 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.5550. Min Act: -0.0000

Data Index: 503509 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.5722. Min Act: -0.0000

Data Index: 64427 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.5610. Min Act: -0.0000

Data Index: 783790 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.4876. Min Act: -0.0000

Data Index: 591936 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.5426. Min Act: -0.0000

Data Index: 753721 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.5355. Min Act: -0.0000

Data Index: 645945 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.5337. Min Act: -0.0000

Data Index: 780174 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.5155. Min Act: -0.0000

Data Index: 393638 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1353666 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.5116. Min Act: -0.0000

Data Index: 742327 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1180022 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.5086. Min Act: -0.0000

Data Index: 482528 (C4 (Web Text))

Max Activating Token Index: 163