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

Dataset: The Pile

Neuron 1233 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.8715. Min Act: 0.0000

Data Index: 923214 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1892999 (The Pile)

Max Activating Token Index: 1014

Text #2

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.8132. Min Act: -0.0000

Data Index: 1217632 (The Pile)

Max Activating Token Index: 449

Text #3

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1072127 (The Pile)

Max Activating Token Index: 45

Text #4

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1603995 (The Pile)

Max Activating Token Index: 755

Text #5

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.7552. Min Act: -0.0000

Data Index: 344263 (The Pile)

Max Activating Token Index: 545

Text #6

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1533343 (The Pile)

Max Activating Token Index: 238

Text #7

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.7566. Min Act: -0.0000

Data Index: 958389 (The Pile)

Max Activating Token Index: 932

Text #8

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.7126. Min Act: -0.0000

Data Index: 446216 (The Pile)

Max Activating Token Index: 366

Text #9

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1479845 (The Pile)

Max Activating Token Index: 717

Text #10

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.7677. Min Act: -0.0000

Data Index: 1363837 (The Pile)

Max Activating Token Index: 194

Text #11

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.7055. Min Act: -0.0000

Data Index: 150387 (The Pile)

Max Activating Token Index: 922

Text #12

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.7143. Min Act: -0.0000

Data Index: 329886 (The Pile)

Max Activating Token Index: 363

Text #13

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.7137. Min Act: -0.0000

Data Index: 1721832 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.7123. Min Act: -0.0000

Data Index: 1291488 (The Pile)

Max Activating Token Index: 78

Text #15

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1331519 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.7123. Min Act: -0.0000

Data Index: 1099404 (The Pile)

Max Activating Token Index: 215

Text #17

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1564835 (The Pile)

Max Activating Token Index: 253

Text #18

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.6965. Min Act: -0.0000

Data Index: 655223 (The Pile)

Max Activating Token Index: 229

Text #19

Max Range: 0.8715. Min Range: -0.8715

Max Act: 0.6826. Min Act: -0.0000

Data Index: 1660373 (The Pile)

Max Activating Token Index: 322