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

Dataset: The Pile

Neuron 883 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2213. Min Act: -0.0000

Data Index: 891401 (The Pile)

Max Activating Token Index: 221

Text #1

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2238. Min Act: -0.0000

Data Index: 542750 (The Pile)

Max Activating Token Index: 51

Text #2

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1748277 (The Pile)

Max Activating Token Index: 317

Text #3

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1129322 (The Pile)

Max Activating Token Index: 134

Text #4

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2297. Min Act: -0.0000

Data Index: 735561 (The Pile)

Max Activating Token Index: 108

Text #5

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1782. Min Act: -0.0000

Data Index: 560154 (The Pile)

Max Activating Token Index: 828

Text #6

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1344881 (The Pile)

Max Activating Token Index: 630

Text #7

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2109. Min Act: -0.0000

Data Index: 47918 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2018. Min Act: -0.0000

Data Index: 1333201 (The Pile)

Max Activating Token Index: 38

Text #9

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1997. Min Act: -0.0000

Data Index: 1254749 (The Pile)

Max Activating Token Index: 51

Text #10

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1620559 (The Pile)

Max Activating Token Index: 465

Text #11

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1987586 (The Pile)

Max Activating Token Index: 435

Text #12

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1142177 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1679618 (The Pile)

Max Activating Token Index: 251

Text #14

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1090166 (The Pile)

Max Activating Token Index: 367

Text #15

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1884. Min Act: -0.0000

Data Index: 1520362 (The Pile)

Max Activating Token Index: 894

Text #16

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1296048 (The Pile)

Max Activating Token Index: 116

Text #17

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1504941 (The Pile)

Max Activating Token Index: 47

Text #18

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1263122 (The Pile)

Max Activating Token Index: 723

Text #19

Max Range: 0.2297. Min Range: -0.2297

Max Act: 0.2078. Min Act: -0.0000

Data Index: 1524684 (The Pile)

Max Activating Token Index: 944