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

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

Neuron 4993 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.1879. Min Act: -0.0000

Data Index: 886479 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.1272. Min Act: -0.0001

Data Index: 619379 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.2768. Min Act: -0.0001

Data Index: 402557 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.1984. Min Act: -0.0000

Data Index: 796255 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0106. Min Act: -0.0001

Data Index: 424876 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.1301. Min Act: -0.0000

Data Index: 284544 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.1667. Min Act: -0.0001

Data Index: 711695 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.1573. Min Act: -0.0001

Data Index: 613784 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0123. Min Act: -0.0001

Data Index: 969007 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.1330. Min Act: -0.0000

Data Index: 638787 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0590. Min Act: -0.0001

Data Index: 426901 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0339. Min Act: -0.0001

Data Index: 671404 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.1076. Min Act: -0.0001

Data Index: 847903 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9842. Min Act: -0.0001

Data Index: 816620 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0575. Min Act: -0.0001

Data Index: 128418 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 1.2768. Min Range: -1.2768

Max Act: 0.9387. Min Act: -0.0001

Data Index: 946758 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0763. Min Act: -0.0001

Data Index: 1113635 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0428. Min Act: -0.0001

Data Index: 623216 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0219. Min Act: -0.0001

Data Index: 278261 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.2768. Min Range: -1.2768

Max Act: 1.0215. Min Act: -0.0001

Data Index: 900141 (C4 (Web Text))

Max Activating Token Index: 492