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

Dataset: The Pile

Neuron 41 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.4883. Min Act: -0.0000

Data Index: 557427 (The Pile)

Max Activating Token Index: 180

Text #1

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.2936. Min Act: -0.0000

Data Index: 1976302 (The Pile)

Max Activating Token Index: 927

Text #2

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.3628. Min Act: -0.0000

Data Index: 1351021 (The Pile)

Max Activating Token Index: 931

Text #3

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.4289. Min Act: 0.0000

Data Index: 1626573 (The Pile)

Max Activating Token Index: 223

Text #4

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.3124. Min Act: -0.0000

Data Index: 1634004 (The Pile)

Max Activating Token Index: 624

Text #5

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.3000. Min Act: -0.0000

Data Index: 405683 (The Pile)

Max Activating Token Index: 183

Text #6

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.2235. Min Act: -0.0000

Data Index: 724514 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.2734. Min Act: 0.0000

Data Index: 1880999 (The Pile)

Max Activating Token Index: 96

Text #8

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.2162. Min Act: -0.0000

Data Index: 1389860 (The Pile)

Max Activating Token Index: 371

Text #9

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.2806. Min Act: -0.0000

Data Index: 77122 (The Pile)

Max Activating Token Index: 618

Text #10

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.1850. Min Act: -0.0000

Data Index: 1323458 (The Pile)

Max Activating Token Index: 223

Text #11

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.0925. Min Act: -0.0000

Data Index: 683799 (The Pile)

Max Activating Token Index: 135

Text #12

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.0747. Min Act: -0.0000

Data Index: 1425661 (The Pile)

Max Activating Token Index: 811

Text #13

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.1500. Min Act: -0.0000

Data Index: 998096 (The Pile)

Max Activating Token Index: 978

Text #14

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.1970. Min Act: -0.0000

Data Index: 514357 (The Pile)

Max Activating Token Index: 875

Text #15

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.1096. Min Act: -0.0000

Data Index: 1559339 (The Pile)

Max Activating Token Index: 870

Text #16

Max Range: 1.4883. Min Range: -1.4883

Max Act: 0.9907. Min Act: -0.0000

Data Index: 1183117 (The Pile)

Max Activating Token Index: 861

Text #17

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.1238. Min Act: 0.0000

Data Index: 859340 (The Pile)

Max Activating Token Index: 628

Text #18

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1387289 (The Pile)

Max Activating Token Index: 270

Text #19

Max Range: 1.4883. Min Range: -1.4883

Max Act: 1.0168. Min Act: -0.0000

Data Index: 596759 (The Pile)

Max Activating Token Index: 568