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

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

Neuron 1272 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: 0.3881. Min Range: -0.3881

Max Act: 0.3881. Min Act: 0.0001

Data Index: 201871 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3819. Min Act: 0.0000

Data Index: 774794 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3640. Min Act: -0.0000

Data Index: 812591 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1260416 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3427. Min Act: -0.0000

Data Index: 556946 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3557. Min Act: -0.0000

Data Index: 455070 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3211. Min Act: -0.0000

Data Index: 519348 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3196. Min Act: -0.0000

Data Index: 867413 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3320. Min Act: 0.0001

Data Index: 178324 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1354106 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3032. Min Act: -0.0000

Data Index: 826659 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1145784 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.2997. Min Act: -0.0000

Data Index: 644481 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.2949. Min Act: -0.0000

Data Index: 388623 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.2925. Min Act: -0.0000

Data Index: 250280 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.3104. Min Act: -0.0000

Data Index: 1006973 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.2800. Min Act: 0.0000

Data Index: 988197 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.2850. Min Act: -0.0000

Data Index: 785491 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.2844. Min Act: 0.0000

Data Index: 775662 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.3881. Min Range: -0.3881

Max Act: 0.2770. Min Act: -0.0000

Data Index: 426224 (C4 (Web Text))

Max Activating Token Index: 848