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

Dataset: The Pile

Neuron 2176 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: 0.9996. Min Range: -0.9996

Max Act: 0.8860. Min Act: -0.0000

Data Index: 1382313 (The Pile)

Max Activating Token Index: 826

Text #1

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.9996. Min Act: -0.0000

Data Index: 198086 (The Pile)

Max Activating Token Index: 656

Text #2

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.8488. Min Act: -0.0000

Data Index: 1138748 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.8022. Min Act: -0.0000

Data Index: 138312 (The Pile)

Max Activating Token Index: 713

Text #4

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7832. Min Act: -0.0000

Data Index: 279606 (The Pile)

Max Activating Token Index: 952

Text #5

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7712. Min Act: -0.0000

Data Index: 430320 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7157. Min Act: -0.0000

Data Index: 930256 (The Pile)

Max Activating Token Index: 908

Text #7

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7562. Min Act: -0.0000

Data Index: 462993 (The Pile)

Max Activating Token Index: 530

Text #8

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7313. Min Act: -0.0000

Data Index: 745548 (The Pile)

Max Activating Token Index: 804

Text #9

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7213. Min Act: -0.0000

Data Index: 1607366 (The Pile)

Max Activating Token Index: 307

Text #10

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1390481 (The Pile)

Max Activating Token Index: 625

Text #11

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6083. Min Act: -0.0000

Data Index: 598870 (The Pile)

Max Activating Token Index: 773

Text #12

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1683214 (The Pile)

Max Activating Token Index: 607

Text #13

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7844. Min Act: -0.0000

Data Index: 600921 (The Pile)

Max Activating Token Index: 178

Text #14

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7173. Min Act: -0.0000

Data Index: 236829 (The Pile)

Max Activating Token Index: 536

Text #15

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7681. Min Act: -0.0000

Data Index: 1262540 (The Pile)

Max Activating Token Index: 974

Text #16

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7050. Min Act: -0.0000

Data Index: 436347 (The Pile)

Max Activating Token Index: 821

Text #17

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1737048 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1146518 (The Pile)

Max Activating Token Index: 1017

Text #19

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1215439 (The Pile)

Max Activating Token Index: 372