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

Dataset: The Pile

Neuron 387 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: 0.9980. Min Range: -0.9980

Max Act: 0.9980. Min Act: -0.0000

Data Index: 1425250 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.9268. Min Act: -0.0000

Data Index: 1820576 (The Pile)

Max Activating Token Index: 965

Text #2

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.9010. Min Act: -0.0000

Data Index: 417519 (The Pile)

Max Activating Token Index: 487

Text #3

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1079213 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8798. Min Act: -0.0000

Data Index: 564752 (The Pile)

Max Activating Token Index: 586

Text #5

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1471406 (The Pile)

Max Activating Token Index: 388

Text #6

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8533. Min Act: -0.0000

Data Index: 563264 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8411. Min Act: -0.0000

Data Index: 307179 (The Pile)

Max Activating Token Index: 778

Text #8

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8370. Min Act: -0.0000

Data Index: 80836 (The Pile)

Max Activating Token Index: 736

Text #9

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8063. Min Act: -0.0000

Data Index: 232779 (The Pile)

Max Activating Token Index: 795

Text #10

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1855229 (The Pile)

Max Activating Token Index: 1011

Text #11

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8165. Min Act: -0.0000

Data Index: 294989 (The Pile)

Max Activating Token Index: 896

Text #12

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1160998 (The Pile)

Max Activating Token Index: 239

Text #13

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7749. Min Act: -0.0000

Data Index: 1945054 (The Pile)

Max Activating Token Index: 640

Text #14

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7711. Min Act: -0.0000

Data Index: 27023 (The Pile)

Max Activating Token Index: 453

Text #15

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6895. Min Act: -0.0000

Data Index: 388134 (The Pile)

Max Activating Token Index: 13

Text #16

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8061. Min Act: -0.0000

Data Index: 1215531 (The Pile)

Max Activating Token Index: 977

Text #17

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7801. Min Act: -0.0000

Data Index: 431255 (The Pile)

Max Activating Token Index: 377

Text #18

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7775. Min Act: -0.0000

Data Index: 1114783 (The Pile)

Max Activating Token Index: 714

Text #19

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7654. Min Act: -0.0000

Data Index: 984403 (The Pile)

Max Activating Token Index: 696