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

Dataset: The Pile

Neuron 881 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1024321 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1481. Min Act: -0.0000

Data Index: 1546385 (The Pile)

Max Activating Token Index: 87

Text #2

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1385. Min Act: -0.0000

Data Index: 733009 (The Pile)

Max Activating Token Index: 665

Text #3

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1409. Min Act: -0.0000

Data Index: 195750 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1435431 (The Pile)

Max Activating Token Index: 263

Text #5

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1347. Min Act: -0.0000

Data Index: 645884 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1761294 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1357. Min Act: -0.0000

Data Index: 604362 (The Pile)

Max Activating Token Index: 27

Text #8

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1279. Min Act: -0.0000

Data Index: 744906 (The Pile)

Max Activating Token Index: 844

Text #9

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1245. Min Act: -0.0000

Data Index: 1959951 (The Pile)

Max Activating Token Index: 206

Text #10

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1380219 (The Pile)

Max Activating Token Index: 552

Text #11

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1202. Min Act: -0.0000

Data Index: 807758 (The Pile)

Max Activating Token Index: 702

Text #12

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1183. Min Act: -0.0000

Data Index: 1050112 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1231. Min Act: -0.0000

Data Index: 1390209 (The Pile)

Max Activating Token Index: 227

Text #14

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1102. Min Act: -0.0000

Data Index: 736032 (The Pile)

Max Activating Token Index: 741

Text #15

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1201. Min Act: -0.0000

Data Index: 1432764 (The Pile)

Max Activating Token Index: 73

Text #16

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1297806 (The Pile)

Max Activating Token Index: 829

Text #17

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1095394 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1018. Min Act: -0.0000

Data Index: 989782 (The Pile)

Max Activating Token Index: 739

Text #19

Max Range: 0.1575. Min Range: -0.1575

Max Act: 0.1175. Min Act: -0.0000

Data Index: 1643570 (The Pile)

Max Activating Token Index: 22