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

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

Neuron 4865 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.7533. Min Act: -0.0001

Data Index: 1265431 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6593. Min Act: -0.0001

Data Index: 1125658 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6303. Min Act: -0.0001

Data Index: 474383 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.6085. Min Act: -0.0001

Data Index: 618410 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.5433. Min Act: -0.0001

Data Index: 68571 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.5408. Min Act: -0.0001

Data Index: 503213 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.5188. Min Act: -0.0001

Data Index: 1300962 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.5484. Min Act: -0.0001

Data Index: 960668 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.4702. Min Act: -0.0001

Data Index: 255404 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.4833. Min Act: -0.0001

Data Index: 800778 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.4995. Min Act: -0.0001

Data Index: 258434 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.5042. Min Act: -0.0001

Data Index: 682291 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.4598. Min Act: -0.0001

Data Index: 1087434 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.4850. Min Act: -0.0001

Data Index: 327749 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.4995. Min Act: -0.0001

Data Index: 488216 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.4145. Min Act: -0.0001

Data Index: 1264055 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.4693. Min Act: -0.0001

Data Index: 316810 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.3880. Min Act: -0.0001

Data Index: 1247935 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.4532. Min Act: -0.0001

Data Index: 731906 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.7533. Min Range: -0.7533

Max Act: 0.4557. Min Act: -0.0001

Data Index: 1174851 (C4 (Web Text))

Max Activating Token Index: 914