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

Dataset: The Pile

Neuron 2003 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: 0.3034. Min Range: -0.3034

Max Act: 0.3034. Min Act: -0.0000

Data Index: 1059573 (The Pile)

Max Activating Token Index: 837

Text #1

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2486. Min Act: -0.0000

Data Index: 221920 (The Pile)

Max Activating Token Index: 213

Text #2

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2086. Min Act: -0.0000

Data Index: 886048 (The Pile)

Max Activating Token Index: 942

Text #3

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2147. Min Act: -0.0000

Data Index: 1173988 (The Pile)

Max Activating Token Index: 128

Text #4

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2140. Min Act: -0.0000

Data Index: 801137 (The Pile)

Max Activating Token Index: 253

Text #5

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1560189 (The Pile)

Max Activating Token Index: 199

Text #6

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1059301 (The Pile)

Max Activating Token Index: 282

Text #7

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1872248 (The Pile)

Max Activating Token Index: 77

Text #8

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2059. Min Act: -0.0000

Data Index: 1869604 (The Pile)

Max Activating Token Index: 471

Text #9

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1859. Min Act: -0.0000

Data Index: 226373 (The Pile)

Max Activating Token Index: 346

Text #10

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1345640 (The Pile)

Max Activating Token Index: 556

Text #11

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1657019 (The Pile)

Max Activating Token Index: 134

Text #12

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2078. Min Act: -0.0000

Data Index: 1312854 (The Pile)

Max Activating Token Index: 761

Text #13

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1993. Min Act: -0.0000

Data Index: 354829 (The Pile)

Max Activating Token Index: 218

Text #14

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1060618 (The Pile)

Max Activating Token Index: 901

Text #15

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1987. Min Act: -0.0000

Data Index: 253870 (The Pile)

Max Activating Token Index: 503

Text #16

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1370246 (The Pile)

Max Activating Token Index: 367

Text #17

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2132. Min Act: -0.0000

Data Index: 1843301 (The Pile)

Max Activating Token Index: 99

Text #18

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1948. Min Act: -0.0000

Data Index: 136201 (The Pile)

Max Activating Token Index: 547

Text #19

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1230506 (The Pile)

Max Activating Token Index: 960