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

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

Neuron 4699 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4608. Min Act: -0.0000

Data Index: 125862 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4806. Min Act: -0.0000

Data Index: 304017 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4814. Min Act: -0.0000

Data Index: 603181 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4582. Min Act: -0.0000

Data Index: 304885 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4572. Min Act: -0.0000

Data Index: 584052 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4266. Min Act: -0.0000

Data Index: 80880 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4327. Min Act: -0.0000

Data Index: 391943 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4421. Min Act: -0.0000

Data Index: 796919 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1119700 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4437. Min Act: -0.0000

Data Index: 467855 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4735. Min Act: -0.0000

Data Index: 929769 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4564. Min Act: -0.0000

Data Index: 1060292 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1344478 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4210. Min Act: -0.0000

Data Index: 993017 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4464. Min Act: -0.0000

Data Index: 922837 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4439. Min Act: -0.0000

Data Index: 715305 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4366. Min Act: -0.0000

Data Index: 906888 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.3862. Min Act: -0.0000

Data Index: 451874 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4191. Min Act: -0.0000

Data Index: 307627 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.4814. Min Range: -0.4814

Max Act: 0.4368. Min Act: -0.0000

Data Index: 265902 (C4 (Web Text))

Max Activating Token Index: 919