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

Dataset: The Pile

Neuron 4197 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: 1.8369. Min Range: -1.8369

Max Act: 1.8369. Min Act: -0.0000

Data Index: 940858 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.5902. Min Act: -0.0000

Data Index: 1578690 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.6309. Min Act: -0.0000

Data Index: 414829 (The Pile)

Max Activating Token Index: 511

Text #3

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.7132. Min Act: -0.0000

Data Index: 857233 (The Pile)

Max Activating Token Index: 491

Text #4

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.5325. Min Act: -0.0000

Data Index: 692512 (The Pile)

Max Activating Token Index: 801

Text #5

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.6049. Min Act: -0.0000

Data Index: 1516542 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.5069. Min Act: -0.0000

Data Index: 494817 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.4109. Min Act: -0.0000

Data Index: 734288 (The Pile)

Max Activating Token Index: 191

Text #8

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.4986. Min Act: -0.0000

Data Index: 196697 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.3928. Min Act: -0.0000

Data Index: 1484897 (The Pile)

Max Activating Token Index: 82

Text #10

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.5167. Min Act: -0.0000

Data Index: 1396380 (The Pile)

Max Activating Token Index: 547

Text #11

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.4175. Min Act: -0.0000

Data Index: 1593267 (The Pile)

Max Activating Token Index: 392

Text #12

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.4081. Min Act: -0.0000

Data Index: 1784920 (The Pile)

Max Activating Token Index: 467

Text #13

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.3915. Min Act: -0.0000

Data Index: 1198967 (The Pile)

Max Activating Token Index: 992

Text #14

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.4012. Min Act: -0.0000

Data Index: 203835 (The Pile)

Max Activating Token Index: 592

Text #15

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.3878. Min Act: -0.0000

Data Index: 1775783 (The Pile)

Max Activating Token Index: 410

Text #16

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.3511. Min Act: -0.0000

Data Index: 1296893 (The Pile)

Max Activating Token Index: 912

Text #17

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.2672. Min Act: -0.0000

Data Index: 1108717 (The Pile)

Max Activating Token Index: 561

Text #18

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.3244. Min Act: -0.0000

Data Index: 1878798 (The Pile)

Max Activating Token Index: 153

Text #19

Max Range: 1.8369. Min Range: -1.8369

Max Act: 1.4123. Min Act: -0.0000

Data Index: 1023854 (The Pile)

Max Activating Token Index: 489