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

Dataset: The Pile

Neuron 1542 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: 0.2442. Min Range: -0.2442

Max Act: 0.2442. Min Act: -0.0000

Data Index: 882442 (The Pile)

Max Activating Token Index: 300

Text #1

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1059839 (The Pile)

Max Activating Token Index: 95

Text #2

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.2100. Min Act: -0.0000

Data Index: 879704 (The Pile)

Max Activating Token Index: 79

Text #3

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1270677 (The Pile)

Max Activating Token Index: 837

Text #4

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1094767 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1164908 (The Pile)

Max Activating Token Index: 942

Text #6

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1140106 (The Pile)

Max Activating Token Index: 868

Text #7

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1980. Min Act: -0.0000

Data Index: 159909 (The Pile)

Max Activating Token Index: 189

Text #8

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1450227 (The Pile)

Max Activating Token Index: 381

Text #9

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1396337 (The Pile)

Max Activating Token Index: 479

Text #10

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1759974 (The Pile)

Max Activating Token Index: 235

Text #11

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1937. Min Act: -0.0000

Data Index: 1265231 (The Pile)

Max Activating Token Index: 186

Text #12

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1036925 (The Pile)

Max Activating Token Index: 757

Text #13

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1800. Min Act: -0.0000

Data Index: 546266 (The Pile)

Max Activating Token Index: 295

Text #14

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1827. Min Act: 0.0000

Data Index: 103046 (The Pile)

Max Activating Token Index: 512

Text #15

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1837. Min Act: -0.0000

Data Index: 138028 (The Pile)

Max Activating Token Index: 508

Text #16

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1820. Min Act: -0.0000

Data Index: 1800586 (The Pile)

Max Activating Token Index: 696

Text #17

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1739. Min Act: -0.0000

Data Index: 146463 (The Pile)

Max Activating Token Index: 723

Text #18

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1777. Min Act: -0.0000

Data Index: 977043 (The Pile)

Max Activating Token Index: 84

Text #19

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1692. Min Act: -0.0000

Data Index: 986585 (The Pile)

Max Activating Token Index: 996