Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1745 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.6561. Min Act: -0.0000

Data Index: 465592 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1193071 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1321341 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4740. Min Act: -0.0000

Data Index: 562526 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4837. Min Act: -0.0000

Data Index: 318385 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4490. Min Act: -0.0000

Data Index: 339344 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1043228 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4233. Min Act: -0.0000

Data Index: 613478 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4264. Min Act: -0.0000

Data Index: 611301 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.3904. Min Act: -0.0000

Data Index: 998633 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.3794. Min Act: -0.0000

Data Index: 865262 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1296063 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.3869. Min Act: 0.0000

Data Index: 1359684 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1167144 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.3845. Min Act: -0.0000

Data Index: 530972 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.3791. Min Act: -0.0000

Data Index: 723896 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.3812. Min Act: -0.0000

Data Index: 1245070 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.3890. Min Act: -0.0000

Data Index: 814691 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1139886 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.6561. Min Range: -0.6561

Max Act: 0.3733. Min Act: 0.0000

Data Index: 801313 (C4 (Web Text))

Max Activating Token Index: 72