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

Dataset: The Pile

Neuron 5010 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.6661. Min Act: -0.0000

Data Index: 313298 (The Pile)

Max Activating Token Index: 766

Text #1

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1223998 (The Pile)

Max Activating Token Index: 72

Text #2

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.4841. Min Act: -0.0000

Data Index: 466107 (The Pile)

Max Activating Token Index: 20

Text #3

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.2078. Min Act: -0.0000

Data Index: 1716731 (The Pile)

Max Activating Token Index: 383

Text #4

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.1852. Min Act: -0.0000

Data Index: 1831646 (The Pile)

Max Activating Token Index: 320

Text #5

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.3195. Min Act: -0.0000

Data Index: 1841715 (The Pile)

Max Activating Token Index: 1020

Text #6

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.2999. Min Act: -0.0000

Data Index: 789854 (The Pile)

Max Activating Token Index: 987

Text #7

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.1652. Min Act: -0.0000

Data Index: 1065789 (The Pile)

Max Activating Token Index: 44

Text #8

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.1491. Min Act: -0.0000

Data Index: 1784449 (The Pile)

Max Activating Token Index: 368

Text #9

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.0114. Min Act: -0.0000

Data Index: 694821 (The Pile)

Max Activating Token Index: 150

Text #10

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.1179. Min Act: -0.0000

Data Index: 664958 (The Pile)

Max Activating Token Index: 32

Text #11

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.2760. Min Act: -0.0000

Data Index: 219438 (The Pile)

Max Activating Token Index: 110

Text #12

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.2412. Min Act: -0.0000

Data Index: 108912 (The Pile)

Max Activating Token Index: 96

Text #13

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.1121. Min Act: -0.0000

Data Index: 518132 (The Pile)

Max Activating Token Index: 876

Text #14

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.1599. Min Act: -0.0000

Data Index: 1955717 (The Pile)

Max Activating Token Index: 777

Text #15

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.1314. Min Act: -0.0000

Data Index: 266713 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 1.6661. Min Range: -1.6661

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1689889 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.1294. Min Act: -0.0000

Data Index: 267857 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.0876. Min Act: -0.0000

Data Index: 1147377 (The Pile)

Max Activating Token Index: 64

Text #19

Max Range: 1.6661. Min Range: -1.6661

Max Act: 1.1301. Min Act: -0.0000

Data Index: 1261210 (The Pile)

Max Activating Token Index: 871