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

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

Neuron 1762 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.3412. Min Act: -0.0001

Data Index: 686350 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.1643. Min Act: -0.0001

Data Index: 179386 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.1921. Min Act: -0.0001

Data Index: 1235235 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.1519. Min Act: -0.0001

Data Index: 812975 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.1037. Min Act: -0.0001

Data Index: 914358 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.0424. Min Act: -0.0001

Data Index: 811263 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.0718. Min Act: -0.0001

Data Index: 887462 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.9371. Min Act: -0.0001

Data Index: 920350 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.0581. Min Act: -0.0001

Data Index: 414922 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.0283. Min Act: -0.0001

Data Index: 439199 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 1.3412. Min Range: -1.3412

Max Act: 1.0549. Min Act: -0.0001

Data Index: 469401 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.9598. Min Act: -0.0001

Data Index: 261780 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.9716. Min Act: -0.0001

Data Index: 64492 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.9417. Min Act: -0.0001

Data Index: 1016997 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.9050. Min Act: -0.0001

Data Index: 1013748 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.9375. Min Act: -0.0001

Data Index: 630667 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.9022. Min Act: -0.0001

Data Index: 360928 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.8778. Min Act: -0.0001

Data Index: 413876 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.9335. Min Act: -0.0001

Data Index: 1182585 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 1.3412. Min Range: -1.3412

Max Act: 0.8759. Min Act: -0.0001

Data Index: 479035 (C4 (Web Text))

Max Activating Token Index: 73