Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1454 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0353. Min Range: -1.0353

Max Act: 1.0353. Min Act: -0.0000

Data Index: 249496 (The Pile)

Max Activating Token Index: 910

Text #1

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.9954. Min Act: -0.0000

Data Index: 712214 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.9144. Min Act: -0.0000

Data Index: 856335 (The Pile)

Max Activating Token Index: 386

Text #3

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.8822. Min Act: -0.0000

Data Index: 631566 (The Pile)

Max Activating Token Index: 241

Text #4

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1118256 (The Pile)

Max Activating Token Index: 245

Text #5

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.8455. Min Act: -0.0000

Data Index: 181930 (The Pile)

Max Activating Token Index: 812

Text #6

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1780547 (The Pile)

Max Activating Token Index: 311

Text #7

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7467. Min Act: -0.0000

Data Index: 256632 (The Pile)

Max Activating Token Index: 283

Text #8

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7568. Min Act: -0.0000

Data Index: 398603 (The Pile)

Max Activating Token Index: 851

Text #9

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7959. Min Act: -0.0000

Data Index: 578060 (The Pile)

Max Activating Token Index: 922

Text #10

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1327510 (The Pile)

Max Activating Token Index: 251

Text #11

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7848. Min Act: -0.0000

Data Index: 781362 (The Pile)

Max Activating Token Index: 417

Text #12

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7603. Min Act: -0.0000

Data Index: 598215 (The Pile)

Max Activating Token Index: 605

Text #13

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1721137 (The Pile)

Max Activating Token Index: 131

Text #14

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7912. Min Act: -0.0000

Data Index: 1300246 (The Pile)

Max Activating Token Index: 188

Text #15

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7333. Min Act: -0.0000

Data Index: 1050228 (The Pile)

Max Activating Token Index: 950

Text #16

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7804. Min Act: -0.0000

Data Index: 1106967 (The Pile)

Max Activating Token Index: 944

Text #17

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7082. Min Act: -0.0000

Data Index: 1996834 (The Pile)

Max Activating Token Index: 793

Text #18

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7729. Min Act: -0.0000

Data Index: 1628656 (The Pile)

Max Activating Token Index: 875

Text #19

Max Range: 1.0353. Min Range: -1.0353

Max Act: 0.7947. Min Act: -0.0000

Data Index: 1878839 (The Pile)

Max Activating Token Index: 871