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

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

Neuron 2684 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.5837. Min Act: -0.0000

Data Index: 321313 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.5136. Min Act: -0.0000

Data Index: 789471 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4558. Min Act: -0.0000

Data Index: 760870 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4360. Min Act: -0.0000

Data Index: 519084 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4357. Min Act: -0.0000

Data Index: 814023 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4239. Min Act: -0.0000

Data Index: 697442 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4097. Min Act: -0.0000

Data Index: 880728 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3928. Min Act: -0.0000

Data Index: 451356 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3842. Min Act: -0.0000

Data Index: 657714 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1032750 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3815. Min Act: -0.0000

Data Index: 883175 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3575. Min Act: 0.0000

Data Index: 493424 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3547. Min Act: -0.0000

Data Index: 1236540 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3758. Min Act: -0.0000

Data Index: 253818 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3416. Min Act: -0.0000

Data Index: 972772 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3417. Min Act: -0.0000

Data Index: 885996 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3350. Min Act: -0.0000

Data Index: 252863 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3454. Min Act: -0.0000

Data Index: 348420 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3251. Min Act: -0.0000

Data Index: 177052 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3086. Min Act: -0.0000

Data Index: 1305953 (C4 (Web Text))

Max Activating Token Index: 247