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

Dataset: The Pile

Neuron 2812 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.3754. Min Act: -0.0000

Data Index: 1644620 (The Pile)

Max Activating Token Index: 191

Text #1

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.2154. Min Act: -0.0000

Data Index: 334789 (The Pile)

Max Activating Token Index: 392

Text #2

Max Range: 1.3754. Min Range: -1.3754

Max Act: 0.9833. Min Act: -0.0000

Data Index: 1525966 (The Pile)

Max Activating Token Index: 53

Text #3

Max Range: 1.3754. Min Range: -1.3754

Max Act: 0.9915. Min Act: -0.0000

Data Index: 30929 (The Pile)

Max Activating Token Index: 869

Text #4

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.0890. Min Act: 0.0000

Data Index: 1818050 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 1.3754. Min Range: -1.3754

Max Act: 0.9469. Min Act: -0.0000

Data Index: 1756033 (The Pile)

Max Activating Token Index: 301

Text #6

Max Range: 1.3754. Min Range: -1.3754

Max Act: 0.8929. Min Act: -0.0000

Data Index: 433194 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.0415. Min Act: -0.0000

Data Index: 515063 (The Pile)

Max Activating Token Index: 226

Text #8

Max Range: 1.3754. Min Range: -1.3754

Max Act: 1.0091. Min Act: -0.0000

Data Index: 788298 (The Pile)

Max Activating Token Index: 770

Text #9

Max Range: 1.3754. Min Range: -1.3754

Max Act: 0.9024. Min Act: 0.0000

Data Index: 1060801 (The Pile)

Max Activating Token Index: 704

Text #10

Max Range: 1.3754. Min Range: -1.3754

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1938463 (The Pile)

Max Activating Token Index: 594

Text #11

Max Range: 1.3754. Min Range: -1.3754

Max Act: 0.9693. Min Act: -0.0000

Data Index: 1454810 (The Pile)

Max Activating Token Index: 65

Text #12

Max Range: 1.3754. Min Range: -1.3754

Max Act: 0.8856. Min Act: -0.0000

Data Index: 286290 (The Pile)

Max Activating Token Index: 364

Text #13

Max Range: 1.3754. Min Range: -1.3754

Max Act: 0.8250. Min Act: -0.0000

Data Index: 1250000 (The Pile)

Max Activating Token Index: 332

Text #14

Max Range: 1.3754. Min Range: -1.3754

Max Act: 0.8912. Min Act: 0.0000

Data Index: 1682616 (The Pile)

Max Activating Token Index: 669

Text #15

Max Range: 1.3754. Min Range: -1.3754

Max Act: 0.7972. Min Act: -0.0000

Data Index: 1425583 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 1.3754. Min Range: -1.3754

Max Act: 0.7489. Min Act: 0.0000

Data Index: 1657329 (The Pile)

Max Activating Token Index: 47

Text #17

Max Range: 1.3754. Min Range: -1.3754

Max Act: 0.8157. Min Act: 0.0000

Data Index: 1870544 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 1.3754. Min Range: -1.3754

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1977998 (The Pile)

Max Activating Token Index: 386

Text #19

Max Range: 1.3754. Min Range: -1.3754

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1666132 (The Pile)

Max Activating Token Index: 461