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

Dataset: The Pile

Neuron 2282 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0056. Min Range: -1.0056

Max Act: 1.0056. Min Act: -0.0000

Data Index: 525241 (The Pile)

Max Activating Token Index: 359

Text #1

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1450321 (The Pile)

Max Activating Token Index: 854

Text #2

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1294481 (The Pile)

Max Activating Token Index: 190

Text #3

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.8101. Min Act: -0.0000

Data Index: 1813750 (The Pile)

Max Activating Token Index: 1019

Text #4

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6928. Min Act: -0.0000

Data Index: 138679 (The Pile)

Max Activating Token Index: 44

Text #5

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7092. Min Act: -0.0000

Data Index: 1952210 (The Pile)

Max Activating Token Index: 881

Text #6

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7322. Min Act: -0.0000

Data Index: 1934019 (The Pile)

Max Activating Token Index: 181

Text #7

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7009. Min Act: -0.0000

Data Index: 1367086 (The Pile)

Max Activating Token Index: 497

Text #8

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7065. Min Act: -0.0000

Data Index: 820963 (The Pile)

Max Activating Token Index: 92

Text #9

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1270725 (The Pile)

Max Activating Token Index: 267

Text #10

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6525. Min Act: -0.0000

Data Index: 425094 (The Pile)

Max Activating Token Index: 10

Text #11

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6847. Min Act: -0.0000

Data Index: 638723 (The Pile)

Max Activating Token Index: 366

Text #12

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1584305 (The Pile)

Max Activating Token Index: 103

Text #13

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6300. Min Act: -0.0000

Data Index: 1142472 (The Pile)

Max Activating Token Index: 492

Text #14

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1460018 (The Pile)

Max Activating Token Index: 48

Text #15

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6206. Min Act: -0.0000

Data Index: 111163 (The Pile)

Max Activating Token Index: 166

Text #16

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6039. Min Act: -0.0000

Data Index: 86506 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1165764 (The Pile)

Max Activating Token Index: 249

Text #18

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6363. Min Act: -0.0000

Data Index: 768231 (The Pile)

Max Activating Token Index: 144

Text #19

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1613641 (The Pile)

Max Activating Token Index: 74