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

Dataset: The Pile

Neuron 2913 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: 0.4774. Min Range: -0.4774

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1347580 (The Pile)

Max Activating Token Index: 894

Text #1

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.4626. Min Act: -0.0000

Data Index: 762882 (The Pile)

Max Activating Token Index: 182

Text #2

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.4306. Min Act: -0.0000

Data Index: 16099 (The Pile)

Max Activating Token Index: 981

Text #3

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1651305 (The Pile)

Max Activating Token Index: 468

Text #4

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3984. Min Act: -0.0000

Data Index: 834977 (The Pile)

Max Activating Token Index: 48

Text #5

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1898059 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3712. Min Act: -0.0000

Data Index: 668032 (The Pile)

Max Activating Token Index: 164

Text #7

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.4003. Min Act: -0.0000

Data Index: 102839 (The Pile)

Max Activating Token Index: 117

Text #8

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1349139 (The Pile)

Max Activating Token Index: 148

Text #9

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3838. Min Act: -0.0000

Data Index: 608262 (The Pile)

Max Activating Token Index: 231

Text #10

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3691. Min Act: -0.0000

Data Index: 218473 (The Pile)

Max Activating Token Index: 412

Text #11

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1867890 (The Pile)

Max Activating Token Index: 418

Text #12

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3485. Min Act: -0.0000

Data Index: 1683495 (The Pile)

Max Activating Token Index: 461

Text #13

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3466. Min Act: -0.0000

Data Index: 77911 (The Pile)

Max Activating Token Index: 762

Text #14

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1472918 (The Pile)

Max Activating Token Index: 761

Text #15

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3406. Min Act: -0.0000

Data Index: 730934 (The Pile)

Max Activating Token Index: 299

Text #16

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3630. Min Act: -0.0000

Data Index: 1981664 (The Pile)

Max Activating Token Index: 561

Text #17

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3519. Min Act: -0.0000

Data Index: 982952 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3471. Min Act: -0.0000

Data Index: 956429 (The Pile)

Max Activating Token Index: 46

Text #19

Max Range: 0.4774. Min Range: -0.4774

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1184057 (The Pile)

Max Activating Token Index: 800