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

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

Neuron 2014 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0495. Min Act: -0.0003

Data Index: 878948 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0492. Min Act: -0.0003

Data Index: 90275 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0435. Min Act: -0.0003

Data Index: 764771 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1209158 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0393. Min Act: -0.0003

Data Index: 965955 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0357. Min Act: -0.0003

Data Index: 648620 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0380. Min Act: -0.0003

Data Index: 2787 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0377. Min Act: -0.0004

Data Index: 1068792 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0392. Min Act: -0.0003

Data Index: 387530 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0369. Min Act: -0.0003

Data Index: 1315922 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0371. Min Act: -0.0003

Data Index: 859504 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0359. Min Act: -0.0003

Data Index: 918038 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0375. Min Act: -0.0003

Data Index: 307071 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0372. Min Act: -0.0003

Data Index: 12367 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0411. Min Act: -0.0003

Data Index: 925300 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0381. Min Act: -0.0003

Data Index: 326728 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0342. Min Act: -0.0004

Data Index: 982342 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0374. Min Act: -0.0003

Data Index: 643204 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1107120 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0349. Min Act: -0.0003

Data Index: 84051 (C4 (Web Text))

Max Activating Token Index: 365