Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1443 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.9822. Min Act: -0.0002

Data Index: 818046 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.8498. Min Act: -0.0002

Data Index: 678613 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.8400. Min Act: -0.0002

Data Index: 636745 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.8165. Min Act: -0.0003

Data Index: 105141 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.8090. Min Act: -0.0002

Data Index: 806244 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.8072. Min Act: -0.0002

Data Index: 381863 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.7787. Min Act: -0.0002

Data Index: 8301 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.7628. Min Act: -0.0002

Data Index: 1173389 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.7797. Min Act: -0.0002

Data Index: 561676 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.7696. Min Act: -0.0002

Data Index: 846343 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.7613. Min Act: -0.0002

Data Index: 1328176 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.7411. Min Act: -0.0002

Data Index: 138131 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.7283. Min Act: -0.0002

Data Index: 448504 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.7330. Min Act: -0.0002

Data Index: 547474 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.7366. Min Act: -0.0002

Data Index: 602922 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.7248. Min Act: -0.0002

Data Index: 459375 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.7310. Min Act: -0.0002

Data Index: 1011055 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.7242. Min Act: -0.0002

Data Index: 1006022 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.7393. Min Act: -0.0002

Data Index: 648745 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.9822. Min Range: -0.9822

Max Act: 0.7371. Min Act: -0.0002

Data Index: 1005893 (C4 (Web Text))

Max Activating Token Index: 22