Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 722 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1871718 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4535. Min Act: -0.0000

Data Index: 680075 (The Pile)

Max Activating Token Index: 897

Text #2

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4829. Min Act: -0.0000

Data Index: 388738 (The Pile)

Max Activating Token Index: 524

Text #3

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4611. Min Act: -0.0000

Data Index: 1676123 (The Pile)

Max Activating Token Index: 501

Text #4

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1661358 (The Pile)

Max Activating Token Index: 24

Text #5

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1835136 (The Pile)

Max Activating Token Index: 60

Text #6

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4593. Min Act: -0.0000

Data Index: 798883 (The Pile)

Max Activating Token Index: 233

Text #7

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4271. Min Act: -0.0000

Data Index: 128732 (The Pile)

Max Activating Token Index: 765

Text #8

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4223. Min Act: -0.0000

Data Index: 897045 (The Pile)

Max Activating Token Index: 212

Text #9

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4324. Min Act: -0.0000

Data Index: 633550 (The Pile)

Max Activating Token Index: 207

Text #10

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4135. Min Act: -0.0000

Data Index: 124808 (The Pile)

Max Activating Token Index: 525

Text #11

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1314688 (The Pile)

Max Activating Token Index: 897

Text #12

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4225. Min Act: -0.0000

Data Index: 138779 (The Pile)

Max Activating Token Index: 547

Text #13

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4184. Min Act: -0.0000

Data Index: 580332 (The Pile)

Max Activating Token Index: 437

Text #14

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3928. Min Act: -0.0000

Data Index: 498218 (The Pile)

Max Activating Token Index: 923

Text #15

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4036. Min Act: -0.0000

Data Index: 995723 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4000. Min Act: -0.0001

Data Index: 1160907 (The Pile)

Max Activating Token Index: 901

Text #17

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4128. Min Act: -0.0000

Data Index: 224923 (The Pile)

Max Activating Token Index: 228

Text #18

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3832. Min Act: -0.0001

Data Index: 1380430 (The Pile)

Max Activating Token Index: 774

Text #19

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1312941 (The Pile)

Max Activating Token Index: 403