Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1470 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1100830 (The Pile)

Max Activating Token Index: 982

Text #1

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1285510 (The Pile)

Max Activating Token Index: 902

Text #2

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1765711 (The Pile)

Max Activating Token Index: 995

Text #3

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2256. Min Act: -0.0000

Data Index: 435965 (The Pile)

Max Activating Token Index: 655

Text #4

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1896629 (The Pile)

Max Activating Token Index: 887

Text #5

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1191841 (The Pile)

Max Activating Token Index: 659

Text #6

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2176. Min Act: -0.0000

Data Index: 880518 (The Pile)

Max Activating Token Index: 448

Text #7

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1180468 (The Pile)

Max Activating Token Index: 266

Text #8

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1155455 (The Pile)

Max Activating Token Index: 1007

Text #9

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1606864 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2154. Min Act: -0.0000

Data Index: 15842 (The Pile)

Max Activating Token Index: 615

Text #11

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2080. Min Act: -0.0000

Data Index: 408895 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2077. Min Act: -0.0000

Data Index: 650835 (The Pile)

Max Activating Token Index: 266

Text #13

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2209. Min Act: -0.0000

Data Index: 97613 (The Pile)

Max Activating Token Index: 356

Text #14

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1983. Min Act: -0.0000

Data Index: 151036 (The Pile)

Max Activating Token Index: 126

Text #15

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1900. Min Act: -0.0000

Data Index: 1706602 (The Pile)

Max Activating Token Index: 545

Text #16

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1934. Min Act: -0.0000

Data Index: 282203 (The Pile)

Max Activating Token Index: 288

Text #17

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1951449 (The Pile)

Max Activating Token Index: 515

Text #18

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1995. Min Act: -0.0000

Data Index: 1735833 (The Pile)

Max Activating Token Index: 712

Text #19

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.1842. Min Act: -0.0000

Data Index: 347659 (The Pile)

Max Activating Token Index: 695