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

Dataset: The Pile

Neuron 4973 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: 1.4301. Min Range: -1.4301

Max Act: 1.4301. Min Act: -0.0000

Data Index: 978305 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.2469. Min Act: -0.0000

Data Index: 419269 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.1804. Min Act: -0.0000

Data Index: 415231 (The Pile)

Max Activating Token Index: 321

Text #3

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.1442. Min Act: -0.0000

Data Index: 27288 (The Pile)

Max Activating Token Index: 824

Text #4

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.2119. Min Act: -0.0000

Data Index: 1554292 (The Pile)

Max Activating Token Index: 378

Text #5

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.1680. Min Act: -0.0000

Data Index: 1982760 (The Pile)

Max Activating Token Index: 396

Text #6

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.1682. Min Act: -0.0000

Data Index: 1421677 (The Pile)

Max Activating Token Index: 268

Text #7

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.1525. Min Act: -0.0000

Data Index: 1010659 (The Pile)

Max Activating Token Index: 999

Text #8

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.1165. Min Act: -0.0000

Data Index: 1583807 (The Pile)

Max Activating Token Index: 179

Text #9

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.0963. Min Act: -0.0000

Data Index: 1797596 (The Pile)

Max Activating Token Index: 283

Text #10

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.1782. Min Act: -0.0000

Data Index: 1848466 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.1106. Min Act: -0.0000

Data Index: 1191156 (The Pile)

Max Activating Token Index: 977

Text #12

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.1423. Min Act: -0.0000

Data Index: 299838 (The Pile)

Max Activating Token Index: 740

Text #13

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.0425. Min Act: -0.0000

Data Index: 827573 (The Pile)

Max Activating Token Index: 976

Text #14

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.0924. Min Act: -0.0000

Data Index: 795382 (The Pile)

Max Activating Token Index: 218

Text #15

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.0989. Min Act: -0.0000

Data Index: 993769 (The Pile)

Max Activating Token Index: 207

Text #16

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.1016. Min Act: -0.0000

Data Index: 955181 (The Pile)

Max Activating Token Index: 462

Text #17

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.0888. Min Act: -0.0000

Data Index: 1130975 (The Pile)

Max Activating Token Index: 958

Text #18

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.0662. Min Act: -0.0000

Data Index: 1054288 (The Pile)

Max Activating Token Index: 861

Text #19

Max Range: 1.4301. Min Range: -1.4301

Max Act: 1.0607. Min Act: -0.0000

Data Index: 874086 (The Pile)

Max Activating Token Index: 496