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

Dataset: The Pile

Neuron 2070 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.8396. Min Act: -0.0000

Data Index: 801287 (The Pile)

Max Activating Token Index: 982

Text #1

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.7425. Min Act: -0.0000

Data Index: 627352 (The Pile)

Max Activating Token Index: 408

Text #2

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1695759 (The Pile)

Max Activating Token Index: 656

Text #3

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1029103 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1595140 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1140589 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5583. Min Act: -0.0000

Data Index: 169326 (The Pile)

Max Activating Token Index: 45

Text #7

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5117. Min Act: -0.0000

Data Index: 543010 (The Pile)

Max Activating Token Index: 988

Text #8

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1850818 (The Pile)

Max Activating Token Index: 926

Text #9

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5042. Min Act: -0.0000

Data Index: 385056 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1474484 (The Pile)

Max Activating Token Index: 802

Text #11

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.4941. Min Act: -0.0000

Data Index: 917009 (The Pile)

Max Activating Token Index: 711

Text #12

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1474596 (The Pile)

Max Activating Token Index: 786

Text #13

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.4966. Min Act: -0.0000

Data Index: 425963 (The Pile)

Max Activating Token Index: 689

Text #14

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.4495. Min Act: -0.0000

Data Index: 295887 (The Pile)

Max Activating Token Index: 604

Text #15

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1969592 (The Pile)

Max Activating Token Index: 162

Text #16

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.4555. Min Act: -0.0000

Data Index: 1999144 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.4851. Min Act: -0.0000

Data Index: 600949 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5543. Min Act: -0.0000

Data Index: 360391 (The Pile)

Max Activating Token Index: 557

Text #19

Max Range: 0.8396. Min Range: -0.8396

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1533147 (The Pile)

Max Activating Token Index: 143