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

Dataset: The Pile

Neuron 2137 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: 1.3749. Min Range: -1.3749

Max Act: 1.2967. Min Act: -0.0000

Data Index: 1614323 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.2917. Min Act: -0.0000

Data Index: 1985034 (The Pile)

Max Activating Token Index: 198

Text #2

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.3666. Min Act: -0.0000

Data Index: 1443000 (The Pile)

Max Activating Token Index: 384

Text #3

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.3283. Min Act: -0.0000

Data Index: 576062 (The Pile)

Max Activating Token Index: 996

Text #4

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.3749. Min Act: -0.0000

Data Index: 1718502 (The Pile)

Max Activating Token Index: 391

Text #5

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.3666. Min Act: -0.0000

Data Index: 1781892 (The Pile)

Max Activating Token Index: 636

Text #6

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1689. Min Act: -0.0000

Data Index: 66178 (The Pile)

Max Activating Token Index: 805

Text #7

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1967. Min Act: -0.0000

Data Index: 469179 (The Pile)

Max Activating Token Index: 153

Text #8

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.2563. Min Act: -0.0000

Data Index: 727755 (The Pile)

Max Activating Token Index: 320

Text #9

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1388. Min Act: -0.0000

Data Index: 235485 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1873. Min Act: -0.0000

Data Index: 796593 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.2184. Min Act: -0.0000

Data Index: 1985253 (The Pile)

Max Activating Token Index: 913

Text #12

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1341. Min Act: -0.0000

Data Index: 484243 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.2190. Min Act: -0.0000

Data Index: 769789 (The Pile)

Max Activating Token Index: 721

Text #14

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.2650. Min Act: -0.0000

Data Index: 646730 (The Pile)

Max Activating Token Index: 838

Text #15

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1170. Min Act: -0.0000

Data Index: 1123729 (The Pile)

Max Activating Token Index: 443

Text #16

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1271. Min Act: -0.0000

Data Index: 706198 (The Pile)

Max Activating Token Index: 343

Text #17

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1927. Min Act: -0.0000

Data Index: 1733099 (The Pile)

Max Activating Token Index: 768

Text #18

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1757. Min Act: -0.0000

Data Index: 706017 (The Pile)

Max Activating Token Index: 728

Text #19

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1100. Min Act: -0.0000

Data Index: 462002 (The Pile)

Max Activating Token Index: 268