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

Dataset: The Pile

Neuron 3735 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.1332. Min Act: -0.0000

Data Index: 953558 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0978. Min Act: -0.0000

Data Index: 471057 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0970. Min Act: -0.0000

Data Index: 1158011 (The Pile)

Max Activating Token Index: 581

Text #3

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1777956 (The Pile)

Max Activating Token Index: 772

Text #4

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0934. Min Act: -0.0000

Data Index: 1810202 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0922. Min Act: -0.0000

Data Index: 1734053 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1847607 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0900. Min Act: -0.0000

Data Index: 363217 (The Pile)

Max Activating Token Index: 7

Text #8

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0864. Min Act: -0.0000

Data Index: 58681 (The Pile)

Max Activating Token Index: 546

Text #9

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0886. Min Act: -0.0000

Data Index: 572636 (The Pile)

Max Activating Token Index: 456

Text #10

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0884. Min Act: -0.0000

Data Index: 663437 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0879. Min Act: -0.0000

Data Index: 367857 (The Pile)

Max Activating Token Index: 609

Text #12

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0877. Min Act: -0.0000

Data Index: 1980503 (The Pile)

Max Activating Token Index: 426

Text #13

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1396719 (The Pile)

Max Activating Token Index: 988

Text #14

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1045019 (The Pile)

Max Activating Token Index: 844

Text #15

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0874. Min Act: -0.0000

Data Index: 56576 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0899. Min Act: -0.0000

Data Index: 1267557 (The Pile)

Max Activating Token Index: 578

Text #17

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1319471 (The Pile)

Max Activating Token Index: 50

Text #18

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1019307 (The Pile)

Max Activating Token Index: 55

Text #19

Max Range: 0.1332. Min Range: -0.1332

Max Act: 0.0857. Min Act: -0.0000

Data Index: 594058 (The Pile)

Max Activating Token Index: 1023