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

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

Neuron 103 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.7879. Min Act: -0.0000

Data Index: 909337 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.5922. Min Act: -0.0000

Data Index: 833958 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.5791. Min Act: -0.0000

Data Index: 608816 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.5023. Min Act: -0.0000

Data Index: 350629 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.5036. Min Act: -0.0000

Data Index: 258733 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.5054. Min Act: -0.0000

Data Index: 4921 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.5223. Min Act: -0.0000

Data Index: 61167 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.5331. Min Act: -0.0000

Data Index: 635022 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.4919. Min Act: -0.0000

Data Index: 698786 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.4701. Min Act: -0.0000

Data Index: 1022194 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.5026. Min Act: -0.0000

Data Index: 352233 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.4765. Min Act: -0.0000

Data Index: 835381 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.4565. Min Act: -0.0000

Data Index: 839402 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.4503. Min Act: -0.0000

Data Index: 145025 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.4490. Min Act: -0.0000

Data Index: 108129 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.4660. Min Act: -0.0000

Data Index: 660628 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.4429. Min Act: -0.0000

Data Index: 346242 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.4425. Min Act: -0.0000

Data Index: 502776 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1153562 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.7879. Min Range: -0.7879

Max Act: 0.4253. Min Act: -0.0000

Data Index: 940631 (C4 (Web Text))

Max Activating Token Index: 643