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

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

Neuron 1415 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.4305. Min Act: -0.0000

Data Index: 650481 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.4192. Min Act: -0.0000

Data Index: 121124 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3845. Min Act: -0.0000

Data Index: 111873 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3436. Min Act: -0.0000

Data Index: 1142869 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3233. Min Act: -0.0000

Data Index: 1170630 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3508. Min Act: -0.0000

Data Index: 494834 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3877. Min Act: -0.0000

Data Index: 576488 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3290. Min Act: -0.0000

Data Index: 517294 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3470. Min Act: -0.0000

Data Index: 329236 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1356368 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.3076. Min Act: -0.0000

Data Index: 586095 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1308139 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.2911. Min Act: -0.0000

Data Index: 155146 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.2822. Min Act: -0.0000

Data Index: 249436 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.2637. Min Act: -0.0000

Data Index: 1048202 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.2811. Min Act: -0.0000

Data Index: 752401 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1221795 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.2810. Min Act: -0.0000

Data Index: 1047797 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.2739. Min Act: -0.0000

Data Index: 251373 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.4305. Min Range: -0.4305

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1127161 (C4 (Web Text))

Max Activating Token Index: 213