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

Dataset: The Pile

Neuron 4257 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: 1.1286. Min Range: -1.1286

Max Act: 1.0500. Min Act: -0.0000

Data Index: 777259 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.9712. Min Act: -0.0000

Data Index: 1564539 (The Pile)

Max Activating Token Index: 110

Text #2

Max Range: 1.1286. Min Range: -1.1286

Max Act: 1.1286. Min Act: -0.0000

Data Index: 755926 (The Pile)

Max Activating Token Index: 625

Text #3

Max Range: 1.1286. Min Range: -1.1286

Max Act: 1.1168. Min Act: -0.0000

Data Index: 1633845 (The Pile)

Max Activating Token Index: 982

Text #4

Max Range: 1.1286. Min Range: -1.1286

Max Act: 1.0120. Min Act: -0.0000

Data Index: 107250 (The Pile)

Max Activating Token Index: 800

Text #5

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1156047 (The Pile)

Max Activating Token Index: 77

Text #6

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1198713 (The Pile)

Max Activating Token Index: 245

Text #7

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1233034 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8619. Min Act: -0.0000

Data Index: 1838495 (The Pile)

Max Activating Token Index: 484

Text #9

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.7018. Min Act: -0.0000

Data Index: 359250 (The Pile)

Max Activating Token Index: 771

Text #10

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1867427 (The Pile)

Max Activating Token Index: 508

Text #11

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1654448 (The Pile)

Max Activating Token Index: 911

Text #12

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.7859. Min Act: -0.0000

Data Index: 613327 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.7908. Min Act: -0.0000

Data Index: 549883 (The Pile)

Max Activating Token Index: 398

Text #14

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.7645. Min Act: -0.0000

Data Index: 1980942 (The Pile)

Max Activating Token Index: 162

Text #15

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.7673. Min Act: -0.0000

Data Index: 484709 (The Pile)

Max Activating Token Index: 293

Text #16

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1323950 (The Pile)

Max Activating Token Index: 796

Text #17

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1302532 (The Pile)

Max Activating Token Index: 986

Text #18

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1982430 (The Pile)

Max Activating Token Index: 695

Text #19

Max Range: 1.1286. Min Range: -1.1286

Max Act: 0.8315. Min Act: -0.0000

Data Index: 31355 (The Pile)

Max Activating Token Index: 575