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

Dataset: The Pile

Neuron 3696 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: 0.7821. Min Range: -0.7821

Max Act: 0.7156. Min Act: -0.0000

Data Index: 1710023 (The Pile)

Max Activating Token Index: 328

Text #1

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.7821. Min Act: -0.0000

Data Index: 1599353 (The Pile)

Max Activating Token Index: 425

Text #2

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6689. Min Act: -0.0000

Data Index: 207039 (The Pile)

Max Activating Token Index: 325

Text #3

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6668. Min Act: -0.0000

Data Index: 614001 (The Pile)

Max Activating Token Index: 673

Text #4

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6837. Min Act: -0.0000

Data Index: 137330 (The Pile)

Max Activating Token Index: 487

Text #5

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6520. Min Act: -0.0000

Data Index: 897843 (The Pile)

Max Activating Token Index: 269

Text #6

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1351417 (The Pile)

Max Activating Token Index: 209

Text #7

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1845494 (The Pile)

Max Activating Token Index: 90

Text #8

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1679967 (The Pile)

Max Activating Token Index: 760

Text #9

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6516. Min Act: -0.0000

Data Index: 431155 (The Pile)

Max Activating Token Index: 511

Text #10

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6295. Min Act: -0.0000

Data Index: 926944 (The Pile)

Max Activating Token Index: 556

Text #11

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6050. Min Act: -0.0000

Data Index: 589071 (The Pile)

Max Activating Token Index: 197

Text #12

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1866393 (The Pile)

Max Activating Token Index: 282

Text #13

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6048. Min Act: -0.0000

Data Index: 722692 (The Pile)

Max Activating Token Index: 572

Text #14

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5794. Min Act: -0.0000

Data Index: 1015109 (The Pile)

Max Activating Token Index: 105

Text #15

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6110. Min Act: -0.0000

Data Index: 354753 (The Pile)

Max Activating Token Index: 174

Text #16

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5744. Min Act: -0.0000

Data Index: 165971 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.6143. Min Act: -0.0000

Data Index: 787765 (The Pile)

Max Activating Token Index: 265

Text #18

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1436307 (The Pile)

Max Activating Token Index: 133

Text #19

Max Range: 0.7821. Min Range: -0.7821

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1829026 (The Pile)

Max Activating Token Index: 993