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

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

Neuron 3002 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0412. Min Range: -1.0412

Max Act: 1.0412. Min Act: -0.0001

Data Index: 534128 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.9155. Min Act: -0.0001

Data Index: 69686 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7785. Min Act: -0.0001

Data Index: 163977 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7887. Min Act: -0.0001

Data Index: 806343 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7479. Min Act: -0.0001

Data Index: 598968 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.8400. Min Act: -0.0001

Data Index: 1350528 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7709. Min Act: -0.0001

Data Index: 787622 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7040. Min Act: -0.0001

Data Index: 540691 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7584. Min Act: -0.0001

Data Index: 145190 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7113. Min Act: -0.0001

Data Index: 302487 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7119. Min Act: -0.0001

Data Index: 1271717 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.7066. Min Act: -0.0001

Data Index: 681154 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.6805. Min Act: -0.0001

Data Index: 637154 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.6714. Min Act: -0.0001

Data Index: 1118897 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.6652. Min Act: -0.0001

Data Index: 1241879 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.6998. Min Act: -0.0001

Data Index: 365340 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.6990. Min Act: -0.0001

Data Index: 281654 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.6733. Min Act: -0.0001

Data Index: 604960 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.6480. Min Act: -0.0001

Data Index: 972210 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 1.0412. Min Range: -1.0412

Max Act: 0.6659. Min Act: -0.0001

Data Index: 670440 (C4 (Web Text))

Max Activating Token Index: 664