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

Dataset: The Pile

Neuron 2331 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.2325. Min Act: -0.0000

Data Index: 879102 (The Pile)

Max Activating Token Index: 551

Text #1

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.2226. Min Act: -0.0000

Data Index: 1395080 (The Pile)

Max Activating Token Index: 25

Text #2

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0852. Min Act: -0.0000

Data Index: 529990 (The Pile)

Max Activating Token Index: 580

Text #3

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0448. Min Act: -0.0000

Data Index: 439227 (The Pile)

Max Activating Token Index: 769

Text #4

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0466. Min Act: -0.0000

Data Index: 1175906 (The Pile)

Max Activating Token Index: 256

Text #5

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0109. Min Act: -0.0000

Data Index: 1167544 (The Pile)

Max Activating Token Index: 154

Text #6

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1252978 (The Pile)

Max Activating Token Index: 658

Text #7

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9886. Min Act: -0.0000

Data Index: 509641 (The Pile)

Max Activating Token Index: 301

Text #8

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9848. Min Act: -0.0000

Data Index: 1931544 (The Pile)

Max Activating Token Index: 552

Text #9

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9371. Min Act: -0.0000

Data Index: 1082771 (The Pile)

Max Activating Token Index: 214

Text #10

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0095. Min Act: -0.0000

Data Index: 756598 (The Pile)

Max Activating Token Index: 752

Text #11

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0442. Min Act: -0.0000

Data Index: 1907305 (The Pile)

Max Activating Token Index: 186

Text #12

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9578. Min Act: -0.0000

Data Index: 869380 (The Pile)

Max Activating Token Index: 9

Text #13

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9028. Min Act: -0.0000

Data Index: 904625 (The Pile)

Max Activating Token Index: 267

Text #14

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9459. Min Act: -0.0000

Data Index: 336947 (The Pile)

Max Activating Token Index: 517

Text #15

Max Range: 1.2325. Min Range: -1.2325

Max Act: 1.0496. Min Act: -0.0000

Data Index: 1939531 (The Pile)

Max Activating Token Index: 226

Text #16

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.8104. Min Act: -0.0000

Data Index: 833919 (The Pile)

Max Activating Token Index: 842

Text #17

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1164813 (The Pile)

Max Activating Token Index: 22

Text #18

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.9081. Min Act: -0.0000

Data Index: 309464 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 1.2325. Min Range: -1.2325

Max Act: 0.8890. Min Act: -0.0000

Data Index: 731374 (The Pile)

Max Activating Token Index: 413