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

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

Neuron 4414 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.7866. Min Act: -0.0000

Data Index: 485617 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.7499. Min Act: -0.0000

Data Index: 20770 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.7021. Min Act: 0.0001

Data Index: 1447496 (Python Code)

Max Activating Token Index: 148

Text #3

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1529160 (Python Code)

Max Activating Token Index: 953

Text #4

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.6615. Min Act: -0.0000

Data Index: 839553 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.6384. Min Act: -0.0000

Data Index: 796869 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.6121. Min Act: 0.0001

Data Index: 1116107 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.6460. Min Act: -0.0000

Data Index: 309544 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.6056. Min Act: -0.0000

Data Index: 258306 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.5718. Min Act: -0.0000

Data Index: 683219 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.5834. Min Act: -0.0000

Data Index: 579542 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.5950. Min Act: -0.0000

Data Index: 78787 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.5887. Min Act: -0.0000

Data Index: 680135 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.5715. Min Act: -0.0000

Data Index: 587661 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.5428. Min Act: -0.0000

Data Index: 645002 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.5706. Min Act: -0.0000

Data Index: 973252 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1141016 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.5342. Min Act: -0.0000

Data Index: 847017 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.5334. Min Act: -0.0000

Data Index: 968193 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.7866. Min Range: -0.7866

Max Act: 0.5223. Min Act: -0.0000

Data Index: 66603 (C4 (Web Text))

Max Activating Token Index: 200