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

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

Neuron 5304 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1101986 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4118. Min Act: -0.0000

Data Index: 646344 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1205868 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3821. Min Act: -0.0000

Data Index: 631255 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3628. Min Act: -0.0000

Data Index: 599588 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4037. Min Act: -0.0000

Data Index: 250190 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3624. Min Act: -0.0000

Data Index: 622578 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3659. Min Act: -0.0000

Data Index: 547754 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3495. Min Act: -0.0000

Data Index: 303061 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3582. Min Act: -0.0000

Data Index: 115436 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3428. Min Act: -0.0000

Data Index: 861119 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1101744 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3497. Min Act: -0.0000

Data Index: 994054 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3357. Min Act: -0.0000

Data Index: 432842 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3338. Min Act: -0.0000

Data Index: 738352 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3154. Min Act: -0.0000

Data Index: 53066 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.2968. Min Act: -0.0000

Data Index: 887235 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3103. Min Act: -0.0000

Data Index: 76658 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3050. Min Act: -0.0000

Data Index: 890390 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1077483 (C4 (Web Text))

Max Activating Token Index: 601