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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2739 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2740. Min Act: 0.0000

Data Index: 42391 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2470. Min Act: -0.0000

Data Index: 100766 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2603. Min Act: -0.0000

Data Index: 751824 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2470. Min Act: -0.0000

Data Index: 31032 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2333. Min Act: 0.0000

Data Index: 885598 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1158307 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2152. Min Act: -0.0000

Data Index: 27810 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2087. Min Act: -0.0000

Data Index: 797194 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2327. Min Act: -0.0000

Data Index: 257573 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2120. Min Act: -0.0000

Data Index: 402 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2184. Min Act: -0.0000

Data Index: 88658 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1900. Min Act: -0.0000

Data Index: 115719 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1151264 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2155. Min Act: -0.0000

Data Index: 1036989 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1254200 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2113. Min Act: -0.0000

Data Index: 240028 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1722. Min Act: -0.0000

Data Index: 37953 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2002. Min Act: 0.0000

Data Index: 884500 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2057. Min Act: -0.0000

Data Index: 263975 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1039320 (C4 (Web Text))

Max Activating Token Index: 251