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

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

Neuron 1039 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: 1.0742. Min Range: -1.0742

Max Act: 1.0742. Min Act: -0.0001

Data Index: 1245416 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 1.0742. Min Range: -1.0742

Max Act: 1.0498. Min Act: -0.0001

Data Index: 852390 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 1.0742. Min Range: -1.0742

Max Act: 1.0511. Min Act: -0.0001

Data Index: 1128214 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 1.0742. Min Range: -1.0742

Max Act: 0.9577. Min Act: -0.0001

Data Index: 65318 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 1.0742. Min Range: -1.0742

Max Act: 0.8611. Min Act: -0.0001

Data Index: 1069160 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 1.0742. Min Range: -1.0742

Max Act: 0.9656. Min Act: -0.0001

Data Index: 714296 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 1.0742. Min Range: -1.0742

Max Act: 0.8538. Min Act: -0.0001

Data Index: 647548 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 1.0742. Min Range: -1.0742

Max Act: 0.8524. Min Act: -0.0001

Data Index: 317804 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 1.0742. Min Range: -1.0742

Max Act: 0.8592. Min Act: -0.0001

Data Index: 133761 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 1.0742. Min Range: -1.0742

Max Act: 0.8856. Min Act: -0.0001

Data Index: 514490 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 1.0742. Min Range: -1.0742

Max Act: 0.8729. Min Act: -0.0001

Data Index: 104844 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 1.0742. Min Range: -1.0742

Max Act: 0.8687. Min Act: -0.0001

Data Index: 968496 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 1.0742. Min Range: -1.0742

Max Act: 0.8224. Min Act: -0.0001

Data Index: 1284648 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 1.0742. Min Range: -1.0742

Max Act: 0.8593. Min Act: -0.0001

Data Index: 807739 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 1.0742. Min Range: -1.0742

Max Act: 0.8565. Min Act: -0.0001

Data Index: 979607 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 1.0742. Min Range: -1.0742

Max Act: 0.9156. Min Act: -0.0001

Data Index: 916010 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 1.0742. Min Range: -1.0742

Max Act: 0.8683. Min Act: -0.0001

Data Index: 739922 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 1.0742. Min Range: -1.0742

Max Act: 0.8130. Min Act: -0.0001

Data Index: 402793 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 1.0742. Min Range: -1.0742

Max Act: 0.8272. Min Act: -0.0000

Data Index: 1169283 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 1.0742. Min Range: -1.0742

Max Act: 0.8214. Min Act: -0.0001

Data Index: 580039 (C4 (Web Text))

Max Activating Token Index: 536