Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3367 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.3267. Min Act: -0.0000

Data Index: 1781073 (The Pile)

Max Activating Token Index: 211

Text #1

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.3051. Min Act: -0.0000

Data Index: 689820 (The Pile)

Max Activating Token Index: 592

Text #2

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1841. Min Act: -0.0000

Data Index: 562161 (The Pile)

Max Activating Token Index: 615

Text #3

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1168. Min Act: -0.0000

Data Index: 1409814 (The Pile)

Max Activating Token Index: 293

Text #4

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1517. Min Act: -0.0000

Data Index: 1121723 (The Pile)

Max Activating Token Index: 389

Text #5

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1532. Min Act: -0.0000

Data Index: 720135 (The Pile)

Max Activating Token Index: 515

Text #6

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1951. Min Act: -0.0000

Data Index: 1469901 (The Pile)

Max Activating Token Index: 397

Text #7

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.2472. Min Act: -0.0000

Data Index: 858650 (The Pile)

Max Activating Token Index: 809

Text #8

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1685. Min Act: -0.0000

Data Index: 530669 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1706. Min Act: -0.0000

Data Index: 1517009 (The Pile)

Max Activating Token Index: 834

Text #10

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1054. Min Act: -0.0000

Data Index: 1690813 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.3191. Min Act: -0.0000

Data Index: 186628 (The Pile)

Max Activating Token Index: 787

Text #12

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1527. Min Act: -0.0000

Data Index: 1094961 (The Pile)

Max Activating Token Index: 52

Text #13

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1390. Min Act: -0.0000

Data Index: 311856 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1165. Min Act: -0.0000

Data Index: 385823 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.0973. Min Act: -0.0000

Data Index: 781487 (The Pile)

Max Activating Token Index: 305

Text #16

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1158. Min Act: -0.0000

Data Index: 819696 (The Pile)

Max Activating Token Index: 133

Text #17

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.0941. Min Act: -0.0000

Data Index: 667686 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1176. Min Act: 0.0000

Data Index: 1566959 (The Pile)

Max Activating Token Index: 111

Text #19

Max Range: 1.3267. Min Range: -1.3267

Max Act: 1.1578. Min Act: -0.0000

Data Index: 1958671 (The Pile)

Max Activating Token Index: 974