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

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

Neuron 2487 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1097. Min Range: -1.1097

Max Act: 0.9249. Min Act: -0.0002

Data Index: 822974 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 1.1097. Min Range: -1.1097

Max Act: 1.0787. Min Act: -0.0002

Data Index: 417830 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 1.1097. Min Range: -1.1097

Max Act: 1.0030. Min Act: -0.0002

Data Index: 1167666 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 1.1097. Min Range: -1.1097

Max Act: 1.0583. Min Act: -0.0002

Data Index: 881351 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 1.1097. Min Range: -1.1097

Max Act: 1.1097. Min Act: -0.0002

Data Index: 945140 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 1.1097. Min Range: -1.1097

Max Act: 0.8374. Min Act: -0.0002

Data Index: 795115 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 1.1097. Min Range: -1.1097

Max Act: 0.8118. Min Act: -0.0002

Data Index: 310203 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 1.1097. Min Range: -1.1097

Max Act: 0.8487. Min Act: -0.0002

Data Index: 540150 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 1.1097. Min Range: -1.1097

Max Act: 0.7908. Min Act: -0.0002

Data Index: 894935 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 1.1097. Min Range: -1.1097

Max Act: 0.6527. Min Act: -0.0002

Data Index: 427783 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 1.1097. Min Range: -1.1097

Max Act: 0.8604. Min Act: -0.0002

Data Index: 504164 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 1.1097. Min Range: -1.1097

Max Act: 0.7549. Min Act: -0.0002

Data Index: 814183 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 1.1097. Min Range: -1.1097

Max Act: 0.8376. Min Act: -0.0002

Data Index: 264417 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 1.1097. Min Range: -1.1097

Max Act: 0.7065. Min Act: -0.0002

Data Index: 1192466 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 1.1097. Min Range: -1.1097

Max Act: 0.7867. Min Act: -0.0002

Data Index: 559642 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 1.1097. Min Range: -1.1097

Max Act: 0.6158. Min Act: -0.0002

Data Index: 352523 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 1.1097. Min Range: -1.1097

Max Act: 0.7144. Min Act: -0.0002

Data Index: 938496 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 1.1097. Min Range: -1.1097

Max Act: 0.7984. Min Act: -0.0002

Data Index: 580779 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 1.1097. Min Range: -1.1097

Max Act: 0.7693. Min Act: -0.0002

Data Index: 140595 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 1.1097. Min Range: -1.1097

Max Act: 0.8124. Min Act: -0.0002

Data Index: 1255157 (C4 (Web Text))

Max Activating Token Index: 125