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

Dataset: The Pile

Neuron 642 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8423. Min Act: -0.0000

Data Index: 47403 (The Pile)

Max Activating Token Index: 119

Text #1

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8408. Min Act: -0.0000

Data Index: 297100 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 1.0173. Min Range: -1.0173

Max Act: 1.0173. Min Act: -0.0000

Data Index: 1109732 (The Pile)

Max Activating Token Index: 897

Text #3

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.9287. Min Act: -0.0000

Data Index: 904773 (The Pile)

Max Activating Token Index: 243

Text #4

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8869. Min Act: -0.0000

Data Index: 555854 (The Pile)

Max Activating Token Index: 199

Text #5

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1185642 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8827. Min Act: -0.0000

Data Index: 524304 (The Pile)

Max Activating Token Index: 441

Text #7

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8725. Min Act: -0.0000

Data Index: 310773 (The Pile)

Max Activating Token Index: 460

Text #8

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8358. Min Act: -0.0000

Data Index: 1740575 (The Pile)

Max Activating Token Index: 68

Text #9

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8332. Min Act: -0.0000

Data Index: 1744287 (The Pile)

Max Activating Token Index: 130

Text #10

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.7771. Min Act: -0.0000

Data Index: 259423 (The Pile)

Max Activating Token Index: 715

Text #11

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8155. Min Act: -0.0000

Data Index: 827388 (The Pile)

Max Activating Token Index: 197

Text #12

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1635572 (The Pile)

Max Activating Token Index: 575

Text #13

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.8095. Min Act: -0.0000

Data Index: 528969 (The Pile)

Max Activating Token Index: 336

Text #14

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.6425. Min Act: -0.0000

Data Index: 884161 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.7848. Min Act: -0.0000

Data Index: 1118635 (The Pile)

Max Activating Token Index: 383

Text #16

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.7558. Min Act: -0.0000

Data Index: 1793261 (The Pile)

Max Activating Token Index: 427

Text #17

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.7757. Min Act: -0.0000

Data Index: 453798 (The Pile)

Max Activating Token Index: 277

Text #18

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.7202. Min Act: -0.0000

Data Index: 742605 (The Pile)

Max Activating Token Index: 606

Text #19

Max Range: 1.0173. Min Range: -1.0173

Max Act: 0.7470. Min Act: -0.0000

Data Index: 1759925 (The Pile)

Max Activating Token Index: 441