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

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

Neuron 368 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: 1.0754. Min Range: -1.0754

Max Act: 0.9063. Min Act: -0.0001

Data Index: 1610198 (Python Code)

Max Activating Token Index: 104

Text #1

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.8234. Min Act: -0.0001

Data Index: 1517341 (Python Code)

Max Activating Token Index: 79

Text #2

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.9471. Min Act: -0.0001

Data Index: 1511431 (Python Code)

Max Activating Token Index: 80

Text #3

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.9921. Min Act: -0.0001

Data Index: 1518413 (Python Code)

Max Activating Token Index: 846

Text #4

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7699. Min Act: -0.0001

Data Index: 1586196 (Python Code)

Max Activating Token Index: 199

Text #5

Max Range: 1.0754. Min Range: -1.0754

Max Act: 1.0754. Min Act: -0.0001

Data Index: 1552074 (Python Code)

Max Activating Token Index: 176

Text #6

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.8391. Min Act: -0.0001

Data Index: 1642598 (Python Code)

Max Activating Token Index: 85

Text #7

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.8476. Min Act: -0.0001

Data Index: 1017423 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7693. Min Act: -0.0001

Data Index: 1367732 (Python Code)

Max Activating Token Index: 94

Text #9

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7849. Min Act: -0.0001

Data Index: 269749 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.8355. Min Act: -0.0001

Data Index: 407303 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7690. Min Act: -0.0001

Data Index: 442603 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7697. Min Act: -0.0001

Data Index: 1546721 (Python Code)

Max Activating Token Index: 33

Text #13

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.8477. Min Act: -0.0001

Data Index: 1646027 (Python Code)

Max Activating Token Index: 422

Text #14

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7707. Min Act: -0.0001

Data Index: 129356 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7593. Min Act: -0.0001

Data Index: 1121257 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7099. Min Act: -0.0001

Data Index: 163392 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7538. Min Act: -0.0001

Data Index: 1402675 (Python Code)

Max Activating Token Index: 53

Text #18

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7479. Min Act: -0.0001

Data Index: 480287 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 1.0754. Min Range: -1.0754

Max Act: 0.7909. Min Act: -0.0001

Data Index: 1601003 (Python Code)

Max Activating Token Index: 425