Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5381 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 4.5611. Min Range: -4.5611

Max Act: 4.5611. Min Act: -0.0002

Data Index: 285865 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 4.5611. Min Range: -4.5611

Max Act: 4.2870. Min Act: -0.0002

Data Index: 210041 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 4.5611. Min Range: -4.5611

Max Act: 4.0640. Min Act: -0.0001

Data Index: 24936 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 4.5611. Min Range: -4.5611

Max Act: 3.9992. Min Act: -0.0001

Data Index: 664498 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 4.5611. Min Range: -4.5611

Max Act: 3.8393. Min Act: -0.0002

Data Index: 820086 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 4.5611. Min Range: -4.5611

Max Act: 3.6735. Min Act: -0.0002

Data Index: 916026 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 4.5611. Min Range: -4.5611

Max Act: 3.6612. Min Act: -0.0002

Data Index: 502405 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 4.5611. Min Range: -4.5611

Max Act: 3.6187. Min Act: -0.0002

Data Index: 1191289 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 4.5611. Min Range: -4.5611

Max Act: 3.6095. Min Act: -0.0002

Data Index: 1117875 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 4.5611. Min Range: -4.5611

Max Act: 3.6676. Min Act: -0.0002

Data Index: 704430 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 4.5611. Min Range: -4.5611

Max Act: 3.5543. Min Act: -0.0002

Data Index: 881128 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 4.5611. Min Range: -4.5611

Max Act: 3.5554. Min Act: -0.0002

Data Index: 702483 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 4.5611. Min Range: -4.5611

Max Act: 3.5089. Min Act: -0.0002

Data Index: 1340133 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 4.5611. Min Range: -4.5611

Max Act: 3.5608. Min Act: -0.0002

Data Index: 1116034 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 4.5611. Min Range: -4.5611

Max Act: 3.4473. Min Act: -0.0002

Data Index: 319227 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 4.5611. Min Range: -4.5611

Max Act: 3.4935. Min Act: -0.0002

Data Index: 825970 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 4.5611. Min Range: -4.5611

Max Act: 3.3873. Min Act: -0.0002

Data Index: 96972 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 4.5611. Min Range: -4.5611

Max Act: 3.4007. Min Act: -0.0002

Data Index: 468684 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 4.5611. Min Range: -4.5611

Max Act: 3.3453. Min Act: -0.0002

Data Index: 923338 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 4.5611. Min Range: -4.5611

Max Act: 3.3071. Min Act: -0.0001

Data Index: 919984 (C4 (Web Text))

Max Activating Token Index: 814