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

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

Neuron 3517 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.9739. Min Act: -0.0000

Data Index: 1040213 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.7445. Min Act: -0.0000

Data Index: 1213034 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.6893. Min Act: -0.0000

Data Index: 773687 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.4969. Min Act: -0.0000

Data Index: 959989 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.4539. Min Act: -0.0000

Data Index: 939636 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.4490. Min Act: -0.0000

Data Index: 316235 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.4116. Min Act: -0.0000

Data Index: 1060748 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.3877. Min Act: -0.0000

Data Index: 220887 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.3701. Min Act: -0.0000

Data Index: 42132 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.3925. Min Act: -0.0000

Data Index: 684864 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.3830. Min Act: -0.0000

Data Index: 173941 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.3678. Min Act: -0.0000

Data Index: 1170794 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.2810. Min Act: -0.0000

Data Index: 188042 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.2709. Min Act: -0.0000

Data Index: 513191 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.3078. Min Act: -0.0000

Data Index: 947669 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.2698. Min Act: -0.0000

Data Index: 1282712 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.1860. Min Act: -0.0000

Data Index: 697337 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.2429. Min Act: -0.0000

Data Index: 958066 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.1924. Min Act: -0.0000

Data Index: 708392 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 1.9739. Min Range: -1.9739

Max Act: 1.2948. Min Act: -0.0000

Data Index: 523399 (C4 (Web Text))

Max Activating Token Index: 1000