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

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

Neuron 4950 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: 0.0670. Min Range: -0.0670

Max Act: 0.0670. Min Act: -0.0002

Data Index: 641037 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1262916 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0582. Min Act: -0.0002

Data Index: 447615 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0619. Min Act: -0.0002

Data Index: 707535 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0585. Min Act: -0.0002

Data Index: 308411 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0617. Min Act: -0.0002

Data Index: 925941 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0570. Min Act: -0.0002

Data Index: 708218 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0606. Min Act: -0.0002

Data Index: 227762 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0538. Min Act: -0.0002

Data Index: 182993 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0527. Min Act: -0.0002

Data Index: 877065 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0500. Min Act: -0.0002

Data Index: 831076 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0540. Min Act: -0.0002

Data Index: 905583 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1320777 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0521. Min Act: -0.0002

Data Index: 858450 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1143011 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0520. Min Act: -0.0002

Data Index: 452073 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0537. Min Act: -0.0002

Data Index: 915423 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0476. Min Act: -0.0002

Data Index: 912820 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1183469 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0517. Min Act: -0.0002

Data Index: 418521 (C4 (Web Text))

Max Activating Token Index: 383