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

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

Neuron 2393 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.5006. Min Act: -0.0001

Data Index: 1145033 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4804. Min Act: -0.0001

Data Index: 1067614 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4166. Min Act: -0.0001

Data Index: 1137097 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4297. Min Act: -0.0001

Data Index: 418642 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4010. Min Act: -0.0001

Data Index: 178425 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3811. Min Act: -0.0001

Data Index: 517117 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3825. Min Act: -0.0001

Data Index: 831193 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3593. Min Act: -0.0001

Data Index: 781880 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3770. Min Act: -0.0001

Data Index: 905166 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3757. Min Act: -0.0001

Data Index: 710067 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3493. Min Act: -0.0001

Data Index: 61627 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3484. Min Act: -0.0001

Data Index: 625952 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3637. Min Act: -0.0001

Data Index: 369429 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3667. Min Act: -0.0001

Data Index: 1289775 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3919. Min Act: -0.0001

Data Index: 1025377 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3796. Min Act: -0.0001

Data Index: 165877 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3741. Min Act: -0.0001

Data Index: 233401 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3731. Min Act: -0.0001

Data Index: 1157579 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3821. Min Act: -0.0001

Data Index: 1263782 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3570. Min Act: -0.0001

Data Index: 356808 (C4 (Web Text))

Max Activating Token Index: 434