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

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

Neuron 4094 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: 1.1156. Min Range: -1.1156

Max Act: 1.0921. Min Act: -0.0002

Data Index: 848929 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 1.1156. Min Range: -1.1156

Max Act: 1.1156. Min Act: -0.0001

Data Index: 414911 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 1.1156. Min Range: -1.1156

Max Act: 1.0288. Min Act: -0.0002

Data Index: 534929 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 1.1156. Min Range: -1.1156

Max Act: 1.0225. Min Act: -0.0002

Data Index: 99643 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 1.1156. Min Range: -1.1156

Max Act: 1.0781. Min Act: -0.0002

Data Index: 816597 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 1.1156. Min Range: -1.1156

Max Act: 1.0373. Min Act: -0.0001

Data Index: 795323 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 1.1156. Min Range: -1.1156

Max Act: 1.0652. Min Act: -0.0002

Data Index: 784698 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.9591. Min Act: -0.0001

Data Index: 20137 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 1.1156. Min Range: -1.1156

Max Act: 1.0104. Min Act: -0.0002

Data Index: 459678 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 1.1156. Min Range: -1.1156

Max Act: 1.1121. Min Act: -0.0001

Data Index: 300006 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.9429. Min Act: -0.0002

Data Index: 535920 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 1.1156. Min Range: -1.1156

Max Act: 1.0283. Min Act: -0.0001

Data Index: 954564 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 1.1156. Min Range: -1.1156

Max Act: 1.0106. Min Act: -0.0002

Data Index: 1001712 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 1.1156. Min Range: -1.1156

Max Act: 1.0807. Min Act: -0.0001

Data Index: 321257 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.9733. Min Act: -0.0001

Data Index: 184695 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.9015. Min Act: -0.0001

Data Index: 709422 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.9032. Min Act: -0.0002

Data Index: 91846 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 1.1156. Min Range: -1.1156

Max Act: 1.0091. Min Act: -0.0002

Data Index: 101566 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.9207. Min Act: -0.0002

Data Index: 859337 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 1.1156. Min Range: -1.1156

Max Act: 0.9767. Min Act: -0.0002

Data Index: 747798 (C4 (Web Text))

Max Activating Token Index: 904