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

Dataset: The Pile

Neuron 5036 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1717868 (The Pile)

Max Activating Token Index: 968

Text #1

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1958678 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2377. Min Act: -0.0000

Data Index: 293103 (The Pile)

Max Activating Token Index: 532

Text #3

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2476. Min Act: -0.0000

Data Index: 397358 (The Pile)

Max Activating Token Index: 353

Text #4

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2233. Min Act: -0.0000

Data Index: 144265 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2174. Min Act: -0.0000

Data Index: 1766971 (The Pile)

Max Activating Token Index: 125

Text #6

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2078. Min Act: -0.0000

Data Index: 769341 (The Pile)

Max Activating Token Index: 924

Text #7

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2236. Min Act: -0.0000

Data Index: 707191 (The Pile)

Max Activating Token Index: 325

Text #8

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2029. Min Act: -0.0000

Data Index: 255557 (The Pile)

Max Activating Token Index: 1005

Text #9

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2148. Min Act: -0.0000

Data Index: 684811 (The Pile)

Max Activating Token Index: 181

Text #10

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1823703 (The Pile)

Max Activating Token Index: 175

Text #11

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1985. Min Act: -0.0000

Data Index: 49544 (The Pile)

Max Activating Token Index: 74

Text #12

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1158982 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1875647 (The Pile)

Max Activating Token Index: 377

Text #14

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1815. Min Act: -0.0000

Data Index: 743113 (The Pile)

Max Activating Token Index: 621

Text #15

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1487934 (The Pile)

Max Activating Token Index: 154

Text #16

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1952. Min Act: -0.0000

Data Index: 261684 (The Pile)

Max Activating Token Index: 955

Text #17

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1951. Min Act: -0.0000

Data Index: 531415 (The Pile)

Max Activating Token Index: 244

Text #18

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1819. Min Act: -0.0000

Data Index: 23343 (The Pile)

Max Activating Token Index: 326

Text #19

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1722. Min Act: -0.0000

Data Index: 703717 (The Pile)

Max Activating Token Index: 291