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

Dataset: The Pile

Neuron 2008 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: 0.2707. Min Range: -0.2707

Max Act: 0.2707. Min Act: 0.0000

Data Index: 1579684 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2148. Min Act: -0.0000

Data Index: 1064903 (The Pile)

Max Activating Token Index: 460

Text #2

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2079. Min Act: -0.0000

Data Index: 280618 (The Pile)

Max Activating Token Index: 993

Text #3

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2036. Min Act: -0.0000

Data Index: 1426693 (The Pile)

Max Activating Token Index: 636

Text #4

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1626079 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.2089. Min Act: -0.0000

Data Index: 181417 (The Pile)

Max Activating Token Index: 71

Text #6

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1921390 (The Pile)

Max Activating Token Index: 469

Text #7

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1939. Min Act: -0.0000

Data Index: 244876 (The Pile)

Max Activating Token Index: 297

Text #8

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1951. Min Act: -0.0000

Data Index: 469643 (The Pile)

Max Activating Token Index: 260

Text #9

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1915494 (The Pile)

Max Activating Token Index: 285

Text #10

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1722. Min Act: -0.0000

Data Index: 1426584 (The Pile)

Max Activating Token Index: 535

Text #11

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1784967 (The Pile)

Max Activating Token Index: 761

Text #12

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1821. Min Act: -0.0000

Data Index: 729191 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1858. Min Act: -0.0000

Data Index: 574271 (The Pile)

Max Activating Token Index: 88

Text #14

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1683505 (The Pile)

Max Activating Token Index: 560

Text #15

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1798. Min Act: -0.0000

Data Index: 224550 (The Pile)

Max Activating Token Index: 216

Text #16

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1784. Min Act: -0.0000

Data Index: 328689 (The Pile)

Max Activating Token Index: 483

Text #17

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1717. Min Act: -0.0000

Data Index: 1981438 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1816. Min Act: -0.0000

Data Index: 1424104 (The Pile)

Max Activating Token Index: 520

Text #19

Max Range: 0.2707. Min Range: -0.2707

Max Act: 0.1748. Min Act: -0.0000

Data Index: 658321 (The Pile)

Max Activating Token Index: 44