Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 871 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.6087. Min Act: -0.0001

Data Index: 1424371 (Python Code)

Max Activating Token Index: 581

Text #1

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1405444 (Python Code)

Max Activating Token Index: 584

Text #2

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.5444. Min Act: -0.0001

Data Index: 1590520 (Python Code)

Max Activating Token Index: 403

Text #3

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.4375. Min Act: -0.0000

Data Index: 1530516 (Python Code)

Max Activating Token Index: 640

Text #4

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.4430. Min Act: -0.0000

Data Index: 1595026 (Python Code)

Max Activating Token Index: 270

Text #5

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1526131 (Python Code)

Max Activating Token Index: 458

Text #6

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.4163. Min Act: -0.0001

Data Index: 1345955 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.4172. Min Act: -0.0001

Data Index: 1640768 (Python Code)

Max Activating Token Index: 690

Text #8

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.4155. Min Act: -0.0001

Data Index: 1501291 (Python Code)

Max Activating Token Index: 503

Text #9

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.4273. Min Act: -0.0000

Data Index: 985638 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3995. Min Act: -0.0000

Data Index: 820803 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3674. Min Act: -0.0001

Data Index: 283451 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3894. Min Act: -0.0000

Data Index: 426399 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3758. Min Act: -0.0001

Data Index: 1008599 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3873. Min Act: -0.0000

Data Index: 98239 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3811. Min Act: -0.0001

Data Index: 1606163 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3717. Min Act: -0.0000

Data Index: 1312187 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3889. Min Act: -0.0000

Data Index: 1051142 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3645. Min Act: -0.0000

Data Index: 604319 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3553. Min Act: -0.0001

Data Index: 208852 (C4 (Web Text))

Max Activating Token Index: 803