Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 787 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2555. Min Act: -0.0002

Data Index: 798360 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2268. Min Act: -0.0002

Data Index: 1800148 (The Pile)

Max Activating Token Index: 129

Text #2

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2240. Min Act: -0.0002

Data Index: 1763515 (The Pile)

Max Activating Token Index: 484

Text #3

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2160. Min Act: -0.0002

Data Index: 155234 (The Pile)

Max Activating Token Index: 305

Text #4

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2097. Min Act: -0.0002

Data Index: 127354 (The Pile)

Max Activating Token Index: 904

Text #5

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2130. Min Act: -0.0002

Data Index: 1494763 (The Pile)

Max Activating Token Index: 465

Text #6

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1955. Min Act: -0.0002

Data Index: 193335 (The Pile)

Max Activating Token Index: 315

Text #7

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1933. Min Act: -0.0002

Data Index: 1189999 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1928. Min Act: -0.0002

Data Index: 957267 (The Pile)

Max Activating Token Index: 353

Text #9

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1977. Min Act: -0.0002

Data Index: 469424 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1912. Min Act: -0.0002

Data Index: 748308 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1960. Min Act: -0.0002

Data Index: 532283 (The Pile)

Max Activating Token Index: 188

Text #12

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1816. Min Act: -0.0002

Data Index: 345897 (The Pile)

Max Activating Token Index: 828

Text #13

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1864. Min Act: -0.0002

Data Index: 1947784 (The Pile)

Max Activating Token Index: 422

Text #14

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1921. Min Act: -0.0002

Data Index: 912512 (The Pile)

Max Activating Token Index: 385

Text #15

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1832. Min Act: -0.0002

Data Index: 1982034 (The Pile)

Max Activating Token Index: 937

Text #16

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1821. Min Act: -0.0002

Data Index: 1262899 (The Pile)

Max Activating Token Index: 68

Text #17

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1820. Min Act: -0.0002

Data Index: 1259727 (The Pile)

Max Activating Token Index: 899

Text #18

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1807. Min Act: -0.0002

Data Index: 394766 (The Pile)

Max Activating Token Index: 616

Text #19

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1791. Min Act: -0.0002

Data Index: 173846 (The Pile)

Max Activating Token Index: 53