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

Dataset: The Pile

Neuron 669 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3713. Min Act: -0.0000

Data Index: 404209 (The Pile)

Max Activating Token Index: 268

Text #1

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2775. Min Act: -0.0000

Data Index: 118955 (The Pile)

Max Activating Token Index: 141

Text #2

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1487020 (The Pile)

Max Activating Token Index: 117

Text #3

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2465. Min Act: -0.0000

Data Index: 633544 (The Pile)

Max Activating Token Index: 914

Text #4

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2099. Min Act: -0.0000

Data Index: 829631 (The Pile)

Max Activating Token Index: 223

Text #5

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2074. Min Act: -0.0000

Data Index: 655622 (The Pile)

Max Activating Token Index: 586

Text #6

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1674254 (The Pile)

Max Activating Token Index: 244

Text #7

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1985. Min Act: -0.0000

Data Index: 1480915 (The Pile)

Max Activating Token Index: 375

Text #8

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1967. Min Act: -0.0000

Data Index: 339886 (The Pile)

Max Activating Token Index: 354

Text #9

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1918491 (The Pile)

Max Activating Token Index: 274

Text #10

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1971194 (The Pile)

Max Activating Token Index: 493

Text #11

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1991. Min Act: -0.0000

Data Index: 327477 (The Pile)

Max Activating Token Index: 98

Text #12

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1891. Min Act: -0.0000

Data Index: 163029 (The Pile)

Max Activating Token Index: 680

Text #13

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1896. Min Act: -0.0000

Data Index: 603651 (The Pile)

Max Activating Token Index: 506

Text #14

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1858. Min Act: -0.0000

Data Index: 1536020 (The Pile)

Max Activating Token Index: 803

Text #15

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1873. Min Act: -0.0000

Data Index: 114995 (The Pile)

Max Activating Token Index: 1005

Text #16

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1194724 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1885339 (The Pile)

Max Activating Token Index: 210

Text #18

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1419318 (The Pile)

Max Activating Token Index: 768

Text #19

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1739. Min Act: -0.0000

Data Index: 372975 (The Pile)

Max Activating Token Index: 660