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

Dataset: The Pile

Neuron 2299 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: 1.9264. Min Range: -1.9264

Max Act: 1.9264. Min Act: -0.0000

Data Index: 1866230 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.7017. Min Act: -0.0000

Data Index: 72831 (The Pile)

Max Activating Token Index: 998

Text #2

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.8238. Min Act: -0.0000

Data Index: 1381777 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.6113. Min Act: -0.0000

Data Index: 133151 (The Pile)

Max Activating Token Index: 88

Text #4

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.6901. Min Act: -0.0000

Data Index: 1337703 (The Pile)

Max Activating Token Index: 132

Text #5

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.7960. Min Act: -0.0000

Data Index: 1174708 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.6958. Min Act: -0.0000

Data Index: 1176840 (The Pile)

Max Activating Token Index: 92

Text #7

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.6915. Min Act: -0.0000

Data Index: 1996769 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.7777. Min Act: -0.0000

Data Index: 1347330 (The Pile)

Max Activating Token Index: 215

Text #9

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.6571. Min Act: -0.0000

Data Index: 932987 (The Pile)

Max Activating Token Index: 535

Text #10

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.5940. Min Act: -0.0000

Data Index: 189826 (The Pile)

Max Activating Token Index: 86

Text #11

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.6245. Min Act: -0.0000

Data Index: 1907753 (The Pile)

Max Activating Token Index: 820

Text #12

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.7496. Min Act: -0.0000

Data Index: 1624445 (The Pile)

Max Activating Token Index: 500

Text #13

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.5598. Min Act: -0.0000

Data Index: 1791548 (The Pile)

Max Activating Token Index: 556

Text #14

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.6358. Min Act: -0.0000

Data Index: 94920 (The Pile)

Max Activating Token Index: 957

Text #15

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.6821. Min Act: -0.0000

Data Index: 1330510 (The Pile)

Max Activating Token Index: 138

Text #16

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.5588. Min Act: -0.0000

Data Index: 1223700 (The Pile)

Max Activating Token Index: 427

Text #17

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.5047. Min Act: -0.0000

Data Index: 1523127 (The Pile)

Max Activating Token Index: 393

Text #18

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.4913. Min Act: -0.0000

Data Index: 785105 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.6103. Min Act: -0.0000

Data Index: 1049140 (The Pile)

Max Activating Token Index: 133