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

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

Neuron 3273 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1370. Min Range: -1.1370

Max Act: 1.1370. Min Act: -0.0000

Data Index: 621531 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 1.1370. Min Range: -1.1370

Max Act: 1.0536. Min Act: -0.0000

Data Index: 624081 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 1.1370. Min Range: -1.1370

Max Act: 1.0767. Min Act: -0.0000

Data Index: 494932 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 1.1370. Min Range: -1.1370

Max Act: 1.0376. Min Act: -0.0000

Data Index: 103823 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 1.1370. Min Range: -1.1370

Max Act: 1.0319. Min Act: -0.0000

Data Index: 1088329 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9793. Min Act: -0.0000

Data Index: 1351248 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9538. Min Act: -0.0001

Data Index: 1650672 (Python Code)

Max Activating Token Index: 399

Text #7

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9655. Min Act: -0.0001

Data Index: 1388911 (Python Code)

Max Activating Token Index: 984

Text #8

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9527. Min Act: -0.0001

Data Index: 1478292 (Python Code)

Max Activating Token Index: 454

Text #9

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9475. Min Act: -0.0000

Data Index: 379760 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9373. Min Act: -0.0000

Data Index: 1313010 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1325350 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1060878 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9207. Min Act: -0.0000

Data Index: 63496 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9722. Min Act: -0.0000

Data Index: 131142 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.8793. Min Act: -0.0001

Data Index: 1414662 (Python Code)

Max Activating Token Index: 505

Text #16

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1004987 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9369. Min Act: -0.0000

Data Index: 423127 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.8964. Min Act: -0.0000

Data Index: 990870 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 1.1370. Min Range: -1.1370

Max Act: 0.9241. Min Act: -0.0000

Data Index: 424513 (C4 (Web Text))

Max Activating Token Index: 665