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

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

Neuron 3506 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2374. Min Range: -1.2374

Max Act: 1.2374. Min Act: -0.0001

Data Index: 1060770 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 1.2374. Min Range: -1.2374

Max Act: 1.2087. Min Act: -0.0001

Data Index: 714784 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 1.2374. Min Range: -1.2374

Max Act: 1.1008. Min Act: -0.0001

Data Index: 1345263 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 1.2374. Min Range: -1.2374

Max Act: 1.0855. Min Act: -0.0001

Data Index: 1071149 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 1.2374. Min Range: -1.2374

Max Act: 1.0661. Min Act: -0.0001

Data Index: 1350340 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 1.2374. Min Range: -1.2374

Max Act: 1.1408. Min Act: -0.0001

Data Index: 72779 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 1.2374. Min Range: -1.2374

Max Act: 1.0911. Min Act: -0.0001

Data Index: 492998 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 1.2374. Min Range: -1.2374

Max Act: 1.0027. Min Act: -0.0001

Data Index: 572749 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 1.2374. Min Range: -1.2374

Max Act: 0.9597. Min Act: -0.0001

Data Index: 482294 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 1.2374. Min Range: -1.2374

Max Act: 0.9505. Min Act: -0.0001

Data Index: 531942 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 1.2374. Min Range: -1.2374

Max Act: 0.8757. Min Act: -0.0001

Data Index: 1283627 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 1.2374. Min Range: -1.2374

Max Act: 0.8720. Min Act: -0.0001

Data Index: 1137227 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 1.2374. Min Range: -1.2374

Max Act: 0.8398. Min Act: -0.0001

Data Index: 1088467 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 1.2374. Min Range: -1.2374

Max Act: 0.8699. Min Act: -0.0001

Data Index: 649646 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 1.2374. Min Range: -1.2374

Max Act: 0.8331. Min Act: -0.0001

Data Index: 79995 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 1.2374. Min Range: -1.2374

Max Act: 0.8021. Min Act: -0.0001

Data Index: 177925 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 1.2374. Min Range: -1.2374

Max Act: 0.8097. Min Act: -0.0001

Data Index: 428853 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 1.2374. Min Range: -1.2374

Max Act: 0.8547. Min Act: -0.0001

Data Index: 161565 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 1.2374. Min Range: -1.2374

Max Act: 0.7909. Min Act: -0.0001

Data Index: 62479 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 1.2374. Min Range: -1.2374

Max Act: 0.8334. Min Act: -0.0001

Data Index: 659578 (C4 (Web Text))

Max Activating Token Index: 784