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

Dataset: The Pile

Neuron 1600 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: 1.1529. Min Range: -1.1529

Max Act: 1.1529. Min Act: -0.0000

Data Index: 47598 (The Pile)

Max Activating Token Index: 399

Text #1

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.8583. Min Act: -0.0000

Data Index: 64180 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.8825. Min Act: -0.0000

Data Index: 441703 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.8207. Min Act: -0.0000

Data Index: 844465 (The Pile)

Max Activating Token Index: 737

Text #4

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.8043. Min Act: -0.0000

Data Index: 930318 (The Pile)

Max Activating Token Index: 928

Text #5

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1628919 (The Pile)

Max Activating Token Index: 272

Text #6

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1101195 (The Pile)

Max Activating Token Index: 904

Text #7

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1910587 (The Pile)

Max Activating Token Index: 881

Text #8

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1646634 (The Pile)

Max Activating Token Index: 424

Text #9

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7482. Min Act: -0.0000

Data Index: 319332 (The Pile)

Max Activating Token Index: 306

Text #10

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7692. Min Act: -0.0000

Data Index: 353255 (The Pile)

Max Activating Token Index: 829

Text #11

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7404. Min Act: -0.0000

Data Index: 1582049 (The Pile)

Max Activating Token Index: 721

Text #12

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7088. Min Act: -0.0000

Data Index: 104848 (The Pile)

Max Activating Token Index: 269

Text #13

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1330999 (The Pile)

Max Activating Token Index: 211

Text #14

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.6642. Min Act: -0.0000

Data Index: 338613 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.6782. Min Act: -0.0000

Data Index: 430097 (The Pile)

Max Activating Token Index: 701

Text #16

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.6693. Min Act: -0.0000

Data Index: 517132 (The Pile)

Max Activating Token Index: 171

Text #17

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.6957. Min Act: -0.0000

Data Index: 1399919 (The Pile)

Max Activating Token Index: 317

Text #18

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.6896. Min Act: -0.0000

Data Index: 203348 (The Pile)

Max Activating Token Index: 56

Text #19

Max Range: 1.1529. Min Range: -1.1529

Max Act: 0.6926. Min Act: -0.0000

Data Index: 435368 (The Pile)

Max Activating Token Index: 1013