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

Dataset: The Pile

Neuron 3717 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.7442. Min Act: -0.0000

Data Index: 1424800 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.7213. Min Act: -0.0000

Data Index: 1167232 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1861852 (The Pile)

Max Activating Token Index: 22

Text #3

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1793225 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1548508 (The Pile)

Max Activating Token Index: 36

Text #5

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6456. Min Act: -0.0000

Data Index: 1553390 (The Pile)

Max Activating Token Index: 14

Text #6

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1332939 (The Pile)

Max Activating Token Index: 1009

Text #7

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6517. Min Act: -0.0000

Data Index: 857173 (The Pile)

Max Activating Token Index: 31

Text #8

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6747. Min Act: -0.0000

Data Index: 10048 (The Pile)

Max Activating Token Index: 286

Text #9

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1070667 (The Pile)

Max Activating Token Index: 14

Text #10

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6598. Min Act: -0.0000

Data Index: 352480 (The Pile)

Max Activating Token Index: 13

Text #11

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1925579 (The Pile)

Max Activating Token Index: 22

Text #12

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6425. Min Act: -0.0000

Data Index: 589205 (The Pile)

Max Activating Token Index: 24

Text #13

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6532. Min Act: -0.0000

Data Index: 375685 (The Pile)

Max Activating Token Index: 22

Text #14

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1085747 (The Pile)

Max Activating Token Index: 138

Text #15

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6273. Min Act: -0.0000

Data Index: 359382 (The Pile)

Max Activating Token Index: 15

Text #16

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6395. Min Act: -0.0000

Data Index: 110978 (The Pile)

Max Activating Token Index: 16

Text #17

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6012. Min Act: -0.0000

Data Index: 346777 (The Pile)

Max Activating Token Index: 164

Text #18

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5671. Min Act: -0.0000

Data Index: 441153 (The Pile)

Max Activating Token Index: 268

Text #19

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1618739 (The Pile)

Max Activating Token Index: 802