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

Dataset: The Pile

Neuron 2043 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: 1.5023. Min Range: -1.5023

Max Act: 1.5023. Min Act: -0.0000

Data Index: 702699 (The Pile)

Max Activating Token Index: 764

Text #1

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.4151. Min Act: -0.0000

Data Index: 1292599 (The Pile)

Max Activating Token Index: 990

Text #2

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.4065. Min Act: -0.0000

Data Index: 1055740 (The Pile)

Max Activating Token Index: 651

Text #3

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.4467. Min Act: -0.0000

Data Index: 17789 (The Pile)

Max Activating Token Index: 375

Text #4

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.1722. Min Act: -0.0000

Data Index: 729123 (The Pile)

Max Activating Token Index: 944

Text #5

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.3032. Min Act: -0.0000

Data Index: 1471168 (The Pile)

Max Activating Token Index: 515

Text #6

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.2630. Min Act: -0.0000

Data Index: 474402 (The Pile)

Max Activating Token Index: 176

Text #7

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.1845. Min Act: -0.0000

Data Index: 151517 (The Pile)

Max Activating Token Index: 235

Text #8

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.1001. Min Act: -0.0000

Data Index: 491422 (The Pile)

Max Activating Token Index: 935

Text #9

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.2263. Min Act: -0.0000

Data Index: 1817425 (The Pile)

Max Activating Token Index: 882

Text #10

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.2225. Min Act: -0.0000

Data Index: 407810 (The Pile)

Max Activating Token Index: 999

Text #11

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.2135. Min Act: -0.0000

Data Index: 829704 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.1906. Min Act: -0.0000

Data Index: 1196962 (The Pile)

Max Activating Token Index: 510

Text #13

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.1793. Min Act: -0.0000

Data Index: 1506989 (The Pile)

Max Activating Token Index: 920

Text #14

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.1676. Min Act: -0.0000

Data Index: 1049580 (The Pile)

Max Activating Token Index: 305

Text #15

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.2084. Min Act: -0.0000

Data Index: 1281522 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.1425. Min Act: -0.0000

Data Index: 1434665 (The Pile)

Max Activating Token Index: 468

Text #17

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.1074. Min Act: -0.0000

Data Index: 1223001 (The Pile)

Max Activating Token Index: 106

Text #18

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.1083. Min Act: -0.0000

Data Index: 135550 (The Pile)

Max Activating Token Index: 512

Text #19

Max Range: 1.5023. Min Range: -1.5023

Max Act: 1.1052. Min Act: -0.0000

Data Index: 1591077 (The Pile)

Max Activating Token Index: 895