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

Dataset: The Pile

Neuron 2626 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.3253. Min Act: -0.0000

Data Index: 1718824 (The Pile)

Max Activating Token Index: 424

Text #1

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2211. Min Act: -0.0000

Data Index: 41804 (The Pile)

Max Activating Token Index: 566

Text #2

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2454. Min Act: -0.0000

Data Index: 246993 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1785185 (The Pile)

Max Activating Token Index: 486

Text #4

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1048987 (The Pile)

Max Activating Token Index: 995

Text #5

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1803. Min Act: -0.0000

Data Index: 334993 (The Pile)

Max Activating Token Index: 945

Text #6

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1387948 (The Pile)

Max Activating Token Index: 388

Text #7

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2280. Min Act: -0.0000

Data Index: 127676 (The Pile)

Max Activating Token Index: 107

Text #8

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2106. Min Act: -0.0000

Data Index: 807244 (The Pile)

Max Activating Token Index: 279

Text #9

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1938. Min Act: -0.0000

Data Index: 33591 (The Pile)

Max Activating Token Index: 74

Text #10

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1787. Min Act: -0.0000

Data Index: 1184178 (The Pile)

Max Activating Token Index: 118

Text #11

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1932. Min Act: -0.0000

Data Index: 535864 (The Pile)

Max Activating Token Index: 426

Text #12

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1929. Min Act: -0.0000

Data Index: 876565 (The Pile)

Max Activating Token Index: 616

Text #13

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1551619 (The Pile)

Max Activating Token Index: 961

Text #14

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1516805 (The Pile)

Max Activating Token Index: 184

Text #15

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.2045. Min Act: -0.0000

Data Index: 485277 (The Pile)

Max Activating Token Index: 264

Text #16

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1812054 (The Pile)

Max Activating Token Index: 753

Text #17

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1888. Min Act: -0.0000

Data Index: 1586115 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1883. Min Act: -0.0000

Data Index: 737308 (The Pile)

Max Activating Token Index: 80

Text #19

Max Range: 0.3253. Min Range: -0.3253

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1293646 (The Pile)

Max Activating Token Index: 516