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

Dataset: The Pile

Neuron 426 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1271. Min Range: -1.1271

Max Act: 1.1271. Min Act: -0.0000

Data Index: 1292525 (The Pile)

Max Activating Token Index: 900

Text #1

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9394. Min Act: -0.0000

Data Index: 927982 (The Pile)

Max Activating Token Index: 876

Text #2

Max Range: 1.1271. Min Range: -1.1271

Max Act: 1.0129. Min Act: -0.0000

Data Index: 1114988 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8880. Min Act: -0.0000

Data Index: 1078799 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.9284. Min Act: -0.0000

Data Index: 1127629 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8005. Min Act: -0.0000

Data Index: 361636 (The Pile)

Max Activating Token Index: 1013

Text #6

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8121. Min Act: -0.0000

Data Index: 443630 (The Pile)

Max Activating Token Index: 607

Text #7

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7133. Min Act: -0.0000

Data Index: 757143 (The Pile)

Max Activating Token Index: 581

Text #8

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1234691 (The Pile)

Max Activating Token Index: 448

Text #9

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7679. Min Act: -0.0000

Data Index: 254436 (The Pile)

Max Activating Token Index: 275

Text #10

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1418033 (The Pile)

Max Activating Token Index: 898

Text #11

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.8173. Min Act: -0.0000

Data Index: 77107 (The Pile)

Max Activating Token Index: 492

Text #12

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7208. Min Act: -0.0000

Data Index: 948512 (The Pile)

Max Activating Token Index: 711

Text #13

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7122. Min Act: -0.0000

Data Index: 1158401 (The Pile)

Max Activating Token Index: 379

Text #14

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7374. Min Act: -0.0000

Data Index: 1338745 (The Pile)

Max Activating Token Index: 167

Text #15

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7604. Min Act: -0.0000

Data Index: 992236 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7729. Min Act: -0.0000

Data Index: 424516 (The Pile)

Max Activating Token Index: 196

Text #17

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7456. Min Act: -0.0000

Data Index: 629542 (The Pile)

Max Activating Token Index: 451

Text #18

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7751. Min Act: -0.0000

Data Index: 188004 (The Pile)

Max Activating Token Index: 464

Text #19

Max Range: 1.1271. Min Range: -1.1271

Max Act: 0.7939. Min Act: -0.0000

Data Index: 1963004 (The Pile)

Max Activating Token Index: 452