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

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

Neuron 2010 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1798. Min Range: -5.1798

Max Act: 5.1798. Min Act: -0.0000

Data Index: 257375 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 5.1798. Min Range: -5.1798

Max Act: 5.1157. Min Act: -0.0000

Data Index: 384042 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.8721. Min Act: -0.0000

Data Index: 1001713 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.4420. Min Act: -0.0000

Data Index: 411441 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.6609. Min Act: -0.0000

Data Index: 299829 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.3684. Min Act: -0.0000

Data Index: 519782 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.4310. Min Act: -0.0000

Data Index: 410174 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.0420. Min Act: -0.0000

Data Index: 1037535 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.1698. Min Act: -0.0000

Data Index: 760356 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.9646. Min Act: -0.0000

Data Index: 178061 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.1004. Min Act: -0.0000

Data Index: 684203 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.0770. Min Act: -0.0000

Data Index: 884540 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.8561. Min Act: -0.0000

Data Index: 194620 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.8371. Min Act: -0.0000

Data Index: 984970 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.8473. Min Act: -0.0000

Data Index: 1234815 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.7820. Min Act: -0.0000

Data Index: 1024114 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.9486. Min Act: -0.0000

Data Index: 871543 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.6087. Min Act: -0.0000

Data Index: 605129 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 5.1798. Min Range: -5.1798

Max Act: 3.9223. Min Act: -0.0000

Data Index: 345963 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 5.1798. Min Range: -5.1798

Max Act: 4.0360. Min Act: -0.0000

Data Index: 1037954 (C4 (Web Text))

Max Activating Token Index: 598