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

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

Neuron 4548 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0927. Min Act: -0.0003

Data Index: 694687 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0888. Min Act: -0.0003

Data Index: 69469 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0858. Min Act: -0.0003

Data Index: 367937 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0806. Min Act: -0.0003

Data Index: 319789 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0787. Min Act: -0.0003

Data Index: 942335 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0785. Min Act: -0.0003

Data Index: 1291474 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0765. Min Act: -0.0003

Data Index: 868896 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0787. Min Act: -0.0003

Data Index: 919228 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0722. Min Act: -0.0003

Data Index: 1033202 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0723. Min Act: -0.0003

Data Index: 1047891 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0747. Min Act: -0.0003

Data Index: 1124369 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0742. Min Act: -0.0003

Data Index: 238407 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0738. Min Act: -0.0003

Data Index: 1192680 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0731. Min Act: -0.0003

Data Index: 987806 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0732. Min Act: -0.0003

Data Index: 48141 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0713. Min Act: -0.0003

Data Index: 819379 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0721. Min Act: -0.0003

Data Index: 981682 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0695. Min Act: -0.0002

Data Index: 311535 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0710. Min Act: -0.0003

Data Index: 113427 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.0927. Min Range: -0.0927

Max Act: 0.0698. Min Act: -0.0003

Data Index: 567697 (C4 (Web Text))

Max Activating Token Index: 340