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

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

Neuron 1013 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: 0.5162. Min Range: -0.5162

Max Act: 0.5162. Min Act: -0.0000

Data Index: 664404 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1372573 (Python Code)

Max Activating Token Index: 66

Text #2

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1632704 (Python Code)

Max Activating Token Index: 959

Text #3

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1327018 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4513. Min Act: -0.0000

Data Index: 462408 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.4206. Min Act: -0.0000

Data Index: 404505 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3892. Min Act: -0.0000

Data Index: 487110 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3825. Min Act: -0.0000

Data Index: 580196 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3837. Min Act: -0.0000

Data Index: 1007205 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3658. Min Act: -0.0000

Data Index: 300198 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3317. Min Act: -0.0000

Data Index: 745642 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3564. Min Act: -0.0000

Data Index: 376616 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3383. Min Act: -0.0000

Data Index: 840436 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1618548 (Python Code)

Max Activating Token Index: 214

Text #14

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3282. Min Act: -0.0000

Data Index: 270005 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3176. Min Act: -0.0000

Data Index: 723274 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3212. Min Act: -0.0000

Data Index: 49766 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1444786 (Python Code)

Max Activating Token Index: 48

Text #18

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.2851. Min Act: -0.0000

Data Index: 496982 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.5162. Min Range: -0.5162

Max Act: 0.3112. Min Act: -0.0000

Data Index: 207986 (C4 (Web Text))

Max Activating Token Index: 605