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

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

Neuron 757 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0608. Min Range: -1.0608

Max Act: 1.0608. Min Act: -0.0000

Data Index: 1203642 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9484. Min Act: -0.0001

Data Index: 254480 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.7299. Min Act: -0.0001

Data Index: 1109758 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.8171. Min Act: -0.0000

Data Index: 858056 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.7415. Min Act: -0.0000

Data Index: 723089 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.7248. Min Act: -0.0000

Data Index: 220773 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.7376. Min Act: -0.0000

Data Index: 402555 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.6737. Min Act: -0.0000

Data Index: 635675 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.6841. Min Act: -0.0000

Data Index: 1557568 (Python Code)

Max Activating Token Index: 328

Text #9

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.6457. Min Act: -0.0000

Data Index: 661116 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.6200. Min Act: -0.0000

Data Index: 975301 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.6264. Min Act: -0.0000

Data Index: 738563 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1291372 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.6380. Min Act: -0.0001

Data Index: 1600690 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1294940 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.5971. Min Act: -0.0000

Data Index: 251250 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.6177. Min Act: -0.0000

Data Index: 562787 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.5869. Min Act: -0.0001

Data Index: 84905 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1501609 (Python Code)

Max Activating Token Index: 546

Text #19

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.5824. Min Act: -0.0000

Data Index: 239509 (C4 (Web Text))

Max Activating Token Index: 66