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

Dataset: The Pile

Neuron 1920 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.7784. Min Act: -0.0000

Data Index: 832019 (The Pile)

Max Activating Token Index: 88

Text #1

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1071992 (The Pile)

Max Activating Token Index: 233

Text #2

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1440783 (The Pile)

Max Activating Token Index: 569

Text #3

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.7253. Min Act: -0.0000

Data Index: 771605 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1603488 (The Pile)

Max Activating Token Index: 166

Text #5

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.6997. Min Act: -0.0000

Data Index: 257718 (The Pile)

Max Activating Token Index: 913

Text #6

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.7166. Min Act: -0.0000

Data Index: 197249 (The Pile)

Max Activating Token Index: 337

Text #7

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.6958. Min Act: -0.0000

Data Index: 114740 (The Pile)

Max Activating Token Index: 77

Text #8

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.7134. Min Act: -0.0000

Data Index: 748924 (The Pile)

Max Activating Token Index: 126

Text #9

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.7489. Min Act: -0.0000

Data Index: 384287 (The Pile)

Max Activating Token Index: 632

Text #10

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.6579. Min Act: -0.0000

Data Index: 813658 (The Pile)

Max Activating Token Index: 483

Text #11

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.6568. Min Act: -0.0000

Data Index: 1634115 (The Pile)

Max Activating Token Index: 570

Text #12

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1525718 (The Pile)

Max Activating Token Index: 23

Text #13

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1957447 (The Pile)

Max Activating Token Index: 180

Text #14

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.6788. Min Act: -0.0000

Data Index: 600570 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1362585 (The Pile)

Max Activating Token Index: 751

Text #16

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.6451. Min Act: -0.0000

Data Index: 819250 (The Pile)

Max Activating Token Index: 486

Text #17

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.6503. Min Act: -0.0000

Data Index: 754041 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.6253. Min Act: -0.0000

Data Index: 541218 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 0.8035. Min Range: -0.8035

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1019491 (The Pile)

Max Activating Token Index: 666