Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 507 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1056777 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0699. Min Act: -0.0002

Data Index: 593701 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0632. Min Act: -0.0002

Data Index: 781172 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1265885 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0647. Min Act: -0.0002

Data Index: 608775 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0615. Min Act: -0.0002

Data Index: 533454 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0606. Min Act: -0.0001

Data Index: 575934 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0599. Min Act: -0.0002

Data Index: 600089 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0597. Min Act: -0.0002

Data Index: 155745 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0598. Min Act: -0.0002

Data Index: 513678 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0590. Min Act: -0.0002

Data Index: 506555 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1286626 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0574. Min Act: -0.0002

Data Index: 34923 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0615. Min Act: -0.0002

Data Index: 857658 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0575. Min Act: -0.0002

Data Index: 73347 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0560. Min Act: -0.0002

Data Index: 294670 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0579. Min Act: -0.0002

Data Index: 987514 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0579. Min Act: -0.0002

Data Index: 978914 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1230120 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0583. Min Act: -0.0002

Data Index: 489933 (C4 (Web Text))

Max Activating Token Index: 73