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

Dataset: The Pile

Neuron 1064 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3822. Min Act: -0.0000

Data Index: 1932047 (The Pile)

Max Activating Token Index: 33

Text #1

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.4154. Min Act: -0.0000

Data Index: 1628018 (The Pile)

Max Activating Token Index: 114

Text #2

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3766. Min Act: -0.0000

Data Index: 130920 (The Pile)

Max Activating Token Index: 29

Text #3

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3587. Min Act: -0.0000

Data Index: 748543 (The Pile)

Max Activating Token Index: 172

Text #4

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3628. Min Act: -0.0000

Data Index: 1276857 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3452. Min Act: -0.0000

Data Index: 1802894 (The Pile)

Max Activating Token Index: 20

Text #6

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3430. Min Act: -0.0000

Data Index: 141687 (The Pile)

Max Activating Token Index: 20

Text #7

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3458. Min Act: -0.0000

Data Index: 461165 (The Pile)

Max Activating Token Index: 339

Text #8

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1302933 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3483. Min Act: -0.0000

Data Index: 1314994 (The Pile)

Max Activating Token Index: 12

Text #10

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1761622 (The Pile)

Max Activating Token Index: 11

Text #11

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1030352 (The Pile)

Max Activating Token Index: 334

Text #12

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1801433 (The Pile)

Max Activating Token Index: 25

Text #13

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1569048 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1606250 (The Pile)

Max Activating Token Index: 15

Text #15

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1830123 (The Pile)

Max Activating Token Index: 34

Text #16

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2982. Min Act: -0.0000

Data Index: 766397 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1791507 (The Pile)

Max Activating Token Index: 52

Text #18

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2943. Min Act: -0.0000

Data Index: 1170658 (The Pile)

Max Activating Token Index: 19

Text #19

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2849. Min Act: -0.0000

Data Index: 1942628 (The Pile)

Max Activating Token Index: 25