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

Dataset: The Pile

Neuron 4950 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2986. Min Act: -0.0000

Data Index: 524502 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2864. Min Act: -0.0000

Data Index: 853532 (The Pile)

Max Activating Token Index: 46

Text #2

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2300. Min Act: -0.0000

Data Index: 342549 (The Pile)

Max Activating Token Index: 483

Text #3

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2139. Min Act: -0.0000

Data Index: 1609652 (The Pile)

Max Activating Token Index: 383

Text #4

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.2757. Min Act: -0.0000

Data Index: 806238 (The Pile)

Max Activating Token Index: 666

Text #5

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.1810. Min Act: -0.0000

Data Index: 1706266 (The Pile)

Max Activating Token Index: 942

Text #6

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.0613. Min Act: -0.0000

Data Index: 384597 (The Pile)

Max Activating Token Index: 48

Text #7

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.0605. Min Act: -0.0000

Data Index: 548338 (The Pile)

Max Activating Token Index: 251

Text #8

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.0469. Min Act: -0.0000

Data Index: 1396310 (The Pile)

Max Activating Token Index: 697

Text #9

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.0505. Min Act: -0.0000

Data Index: 1080321 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.0350. Min Act: -0.0000

Data Index: 600114 (The Pile)

Max Activating Token Index: 653

Text #11

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.0978. Min Act: -0.0000

Data Index: 749507 (The Pile)

Max Activating Token Index: 719

Text #12

Max Range: 1.2986. Min Range: -1.2986

Max Act: 0.9848. Min Act: -0.0000

Data Index: 1686066 (The Pile)

Max Activating Token Index: 979

Text #13

Max Range: 1.2986. Min Range: -1.2986

Max Act: 0.9721. Min Act: -0.0000

Data Index: 1921477 (The Pile)

Max Activating Token Index: 292

Text #14

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.0042. Min Act: -0.0000

Data Index: 212099 (The Pile)

Max Activating Token Index: 687

Text #15

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.0014. Min Act: -0.0000

Data Index: 58733 (The Pile)

Max Activating Token Index: 993

Text #16

Max Range: 1.2986. Min Range: -1.2986

Max Act: 0.9717. Min Act: -0.0000

Data Index: 884715 (The Pile)

Max Activating Token Index: 54

Text #17

Max Range: 1.2986. Min Range: -1.2986

Max Act: 0.9761. Min Act: -0.0000

Data Index: 884069 (The Pile)

Max Activating Token Index: 647

Text #18

Max Range: 1.2986. Min Range: -1.2986

Max Act: 1.0015. Min Act: -0.0000

Data Index: 1956045 (The Pile)

Max Activating Token Index: 574

Text #19

Max Range: 1.2986. Min Range: -1.2986

Max Act: 0.9964. Min Act: -0.0000

Data Index: 1028915 (The Pile)

Max Activating Token Index: 319