Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3594 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.1392. Min Act: -0.0001

Data Index: 670174 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 1.1392. Min Range: -1.1392

Max Act: 1.0876. Min Act: -0.0002

Data Index: 1134005 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.8762. Min Act: -0.0002

Data Index: 463632 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.9373. Min Act: -0.0002

Data Index: 147370 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.8845. Min Act: -0.0001

Data Index: 667897 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.8835. Min Act: -0.0002

Data Index: 1035810 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.8740. Min Act: -0.0002

Data Index: 655741 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.7642. Min Act: -0.0001

Data Index: 527199 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.7796. Min Act: -0.0002

Data Index: 90208 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.7821. Min Act: -0.0002

Data Index: 117061 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.8048. Min Act: -0.0001

Data Index: 625492 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.7273. Min Act: -0.0002

Data Index: 1105221 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.7030. Min Act: -0.0002

Data Index: 1282799 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.6909. Min Act: -0.0002

Data Index: 589820 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.6618. Min Act: -0.0001

Data Index: 745324 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.7425. Min Act: -0.0002

Data Index: 267363 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.6731. Min Act: -0.0001

Data Index: 828389 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.7078. Min Act: -0.0001

Data Index: 301479 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.6916. Min Act: -0.0002

Data Index: 740628 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 1.1392. Min Range: -1.1392

Max Act: 0.6112. Min Act: -0.0002

Data Index: 90770 (C4 (Web Text))

Max Activating Token Index: 811