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

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

Neuron 1941 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4625. Min Act: -0.0000

Data Index: 1056467 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.5595. Min Act: -0.0000

Data Index: 974833 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.5135. Min Act: -0.0000

Data Index: 741812 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.5241. Min Act: -0.0000

Data Index: 24416 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.5051. Min Act: -0.0000

Data Index: 662205 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4512. Min Act: -0.0000

Data Index: 1303094 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4375. Min Act: -0.0000

Data Index: 172163 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4320. Min Act: -0.0000

Data Index: 196487 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1413430 (Python Code)

Max Activating Token Index: 128

Text #9

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1016741 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4117. Min Act: -0.0000

Data Index: 287974 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1607418 (Python Code)

Max Activating Token Index: 269

Text #12

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1530703 (Python Code)

Max Activating Token Index: 170

Text #13

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1319683 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4083. Min Act: -0.0000

Data Index: 1082973 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4298. Min Act: -0.0000

Data Index: 588271 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4027. Min Act: -0.0000

Data Index: 29044 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.4023. Min Act: -0.0000

Data Index: 959694 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.3938. Min Act: -0.0000

Data Index: 814783 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.5595. Min Range: -0.5595

Max Act: 0.3494. Min Act: -0.0000

Data Index: 445221 (C4 (Web Text))

Max Activating Token Index: 733