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

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

Neuron 617 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.5940. Min Act: -0.0002

Data Index: 331603 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.8318. Min Act: -0.0002

Data Index: 15283 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.5851. Min Act: -0.0002

Data Index: 713810 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.6749. Min Act: -0.0002

Data Index: 1028458 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.7906. Min Act: -0.0001

Data Index: 182688 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.8902. Min Act: -0.0001

Data Index: 1047908 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.6564. Min Act: -0.0002

Data Index: 227213 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.3622. Min Act: -0.0001

Data Index: 172620 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.6028. Min Act: -0.0001

Data Index: 172695 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.6831. Min Act: -0.0002

Data Index: 1171281 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.5716. Min Act: -0.0002

Data Index: 722416 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 3.0087. Min Range: -3.0087

Max Act: 3.0087. Min Act: -0.0002

Data Index: 1063836 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.7960. Min Act: -0.0001

Data Index: 1255655 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.6830. Min Act: -0.0002

Data Index: 816036 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.5656. Min Act: -0.0002

Data Index: 779429 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.7441. Min Act: -0.0001

Data Index: 328368 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.5089. Min Act: -0.0002

Data Index: 171858 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.6389. Min Act: -0.0002

Data Index: 163852 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.5919. Min Act: -0.0002

Data Index: 192993 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 3.0087. Min Range: -3.0087

Max Act: 2.5665. Min Act: -0.0002

Data Index: 225506 (C4 (Web Text))

Max Activating Token Index: 212