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

Dataset: The Pile

Neuron 2877 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1813447 (The Pile)

Max Activating Token Index: 232

Text #1

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1552868 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1236259 (The Pile)

Max Activating Token Index: 779

Text #3

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1043388 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2605. Min Act: -0.0000

Data Index: 1414165 (The Pile)

Max Activating Token Index: 203

Text #5

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2878. Min Act: -0.0000

Data Index: 800787 (The Pile)

Max Activating Token Index: 962

Text #6

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1828624 (The Pile)

Max Activating Token Index: 728

Text #7

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2486. Min Act: -0.0000

Data Index: 310397 (The Pile)

Max Activating Token Index: 772

Text #8

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2459. Min Act: -0.0000

Data Index: 316398 (The Pile)

Max Activating Token Index: 1014

Text #9

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2367. Min Act: -0.0000

Data Index: 610134 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1785330 (The Pile)

Max Activating Token Index: 290

Text #11

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2252. Min Act: -0.0000

Data Index: 215181 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1056057 (The Pile)

Max Activating Token Index: 106

Text #13

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2300. Min Act: -0.0000

Data Index: 797117 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2178. Min Act: -0.0000

Data Index: 418097 (The Pile)

Max Activating Token Index: 789

Text #15

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2187. Min Act: -0.0000

Data Index: 1275174 (The Pile)

Max Activating Token Index: 737

Text #16

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2204. Min Act: -0.0000

Data Index: 167974 (The Pile)

Max Activating Token Index: 1010

Text #17

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2215. Min Act: -0.0000

Data Index: 441519 (The Pile)

Max Activating Token Index: 559

Text #18

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2216. Min Act: -0.0000

Data Index: 1362273 (The Pile)

Max Activating Token Index: 715

Text #19

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2138. Min Act: -0.0000

Data Index: 150072 (The Pile)

Max Activating Token Index: 488