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

Dataset: The Pile

Neuron 1611 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: 0.2890. Min Range: -0.2890

Max Act: 0.2890. Min Act: -0.0000

Data Index: 353126 (The Pile)

Max Activating Token Index: 276

Text #1

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2228. Min Act: -0.0000

Data Index: 850013 (The Pile)

Max Activating Token Index: 327

Text #2

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2121. Min Act: -0.0000

Data Index: 425466 (The Pile)

Max Activating Token Index: 995

Text #3

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2069. Min Act: -0.0000

Data Index: 337002 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1557276 (The Pile)

Max Activating Token Index: 871

Text #5

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1729669 (The Pile)

Max Activating Token Index: 681

Text #6

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1882. Min Act: -0.0000

Data Index: 1013766 (The Pile)

Max Activating Token Index: 755

Text #7

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1629654 (The Pile)

Max Activating Token Index: 61

Text #8

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.2024. Min Act: -0.0000

Data Index: 506923 (The Pile)

Max Activating Token Index: 202

Text #9

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1578192 (The Pile)

Max Activating Token Index: 372

Text #10

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1233876 (The Pile)

Max Activating Token Index: 186

Text #11

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1015727 (The Pile)

Max Activating Token Index: 800

Text #12

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1978418 (The Pile)

Max Activating Token Index: 1019

Text #13

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1960. Min Act: -0.0000

Data Index: 892472 (The Pile)

Max Activating Token Index: 748

Text #14

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1894. Min Act: -0.0000

Data Index: 947441 (The Pile)

Max Activating Token Index: 607

Text #15

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1757. Min Act: -0.0000

Data Index: 706899 (The Pile)

Max Activating Token Index: 474

Text #16

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1779. Min Act: -0.0000

Data Index: 1395183 (The Pile)

Max Activating Token Index: 941

Text #17

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1899702 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1802. Min Act: -0.0000

Data Index: 873560 (The Pile)

Max Activating Token Index: 218

Text #19

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1645. Min Act: -0.0000

Data Index: 220810 (The Pile)

Max Activating Token Index: 334