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

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

Neuron 4992 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: 0.5798. Min Range: -0.5798

Max Act: 0.5798. Min Act: -0.0001

Data Index: 1277960 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.5460. Min Act: -0.0001

Data Index: 794701 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.5705. Min Act: -0.0001

Data Index: 797464 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.5245. Min Act: -0.0001

Data Index: 1153382 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.5397. Min Act: -0.0001

Data Index: 407466 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.5320. Min Act: -0.0001

Data Index: 17739 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1002739 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.5349. Min Act: -0.0001

Data Index: 948502 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.5054. Min Act: -0.0001

Data Index: 1230378 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.4819. Min Act: -0.0001

Data Index: 177371 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.4792. Min Act: -0.0001

Data Index: 649738 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.4744. Min Act: -0.0001

Data Index: 1245943 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.4551. Min Act: -0.0001

Data Index: 724925 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.4664. Min Act: -0.0001

Data Index: 10438 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.4996. Min Act: -0.0001

Data Index: 870033 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.4740. Min Act: -0.0001

Data Index: 1223138 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.4529. Min Act: -0.0001

Data Index: 141698 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.4508. Min Act: -0.0001

Data Index: 1066103 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.4519. Min Act: -0.0001

Data Index: 72677 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.5798. Min Range: -0.5798

Max Act: 0.4505. Min Act: -0.0001

Data Index: 216135 (C4 (Web Text))

Max Activating Token Index: 681