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

Dataset: The Pile

Neuron 43 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.9124. Min Act: 0.0000

Data Index: 756843 (The Pile)

Max Activating Token Index: 414

Text #1

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.9749. Min Act: -0.0000

Data Index: 159890 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1098629 (The Pile)

Max Activating Token Index: 464

Text #3

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1195113 (The Pile)

Max Activating Token Index: 302

Text #4

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.9406. Min Act: -0.0000

Data Index: 1428423 (The Pile)

Max Activating Token Index: 189

Text #5

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.8454. Min Act: -0.0000

Data Index: 1748582 (The Pile)

Max Activating Token Index: 210

Text #6

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.8419. Min Act: 0.0001

Data Index: 1125797 (The Pile)

Max Activating Token Index: 695

Text #7

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1178965 (The Pile)

Max Activating Token Index: 136

Text #8

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.9035. Min Act: -0.0000

Data Index: 81667 (The Pile)

Max Activating Token Index: 572

Text #9

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.8956. Min Act: 0.0000

Data Index: 1041723 (The Pile)

Max Activating Token Index: 723

Text #10

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.7806. Min Act: -0.0000

Data Index: 1744114 (The Pile)

Max Activating Token Index: 651

Text #11

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.7573. Min Act: -0.0000

Data Index: 545465 (The Pile)

Max Activating Token Index: 699

Text #12

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1182516 (The Pile)

Max Activating Token Index: 442

Text #13

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1745972 (The Pile)

Max Activating Token Index: 329

Text #14

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.7616. Min Act: -0.0000

Data Index: 1395249 (The Pile)

Max Activating Token Index: 245

Text #15

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.7440. Min Act: -0.0000

Data Index: 497986 (The Pile)

Max Activating Token Index: 583

Text #16

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.7871. Min Act: -0.0000

Data Index: 618453 (The Pile)

Max Activating Token Index: 286

Text #17

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.7180. Min Act: -0.0000

Data Index: 1996074 (The Pile)

Max Activating Token Index: 512

Text #18

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.7505. Min Act: -0.0000

Data Index: 174930 (The Pile)

Max Activating Token Index: 791

Text #19

Max Range: 0.9885. Min Range: -0.9885

Max Act: 0.7722. Min Act: -0.0000

Data Index: 580260 (The Pile)

Max Activating Token Index: 500