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

Dataset: The Pile

Neuron 32 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: 3.6528. Min Range: -3.6528

Max Act: 3.6528. Min Act: -0.0000

Data Index: 538356 (The Pile)

Max Activating Token Index: 527

Text #1

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.4402. Min Act: -0.0000

Data Index: 1892718 (The Pile)

Max Activating Token Index: 870

Text #2

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3193. Min Act: -0.0000

Data Index: 85395 (The Pile)

Max Activating Token Index: 765

Text #3

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.1073. Min Act: -0.0000

Data Index: 1707926 (The Pile)

Max Activating Token Index: 504

Text #4

Max Range: 3.6528. Min Range: -3.6528

Max Act: 2.9862. Min Act: -0.0000

Data Index: 1872812 (The Pile)

Max Activating Token Index: 686

Text #5

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.0444. Min Act: -0.0000

Data Index: 1248690 (The Pile)

Max Activating Token Index: 453

Text #6

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.3092. Min Act: -0.0000

Data Index: 1588271 (The Pile)

Max Activating Token Index: 940

Text #7

Max Range: 3.6528. Min Range: -3.6528

Max Act: 2.9428. Min Act: -0.0000

Data Index: 381754 (The Pile)

Max Activating Token Index: 694

Text #8

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.0658. Min Act: -0.0000

Data Index: 193198 (The Pile)

Max Activating Token Index: 38

Text #9

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.0336. Min Act: -0.0000

Data Index: 669315 (The Pile)

Max Activating Token Index: 763

Text #10

Max Range: 3.6528. Min Range: -3.6528

Max Act: 3.1802. Min Act: -0.0000

Data Index: 1576858 (The Pile)

Max Activating Token Index: 670

Text #11

Max Range: 3.6528. Min Range: -3.6528

Max Act: 2.8754. Min Act: -0.0000

Data Index: 1164251 (The Pile)

Max Activating Token Index: 560

Text #12

Max Range: 3.6528. Min Range: -3.6528

Max Act: 2.8677. Min Act: -0.0000

Data Index: 709052 (The Pile)

Max Activating Token Index: 65

Text #13

Max Range: 3.6528. Min Range: -3.6528

Max Act: 2.9828. Min Act: -0.0000

Data Index: 1331653 (The Pile)

Max Activating Token Index: 233

Text #14

Max Range: 3.6528. Min Range: -3.6528

Max Act: 2.9776. Min Act: -0.0000

Data Index: 471349 (The Pile)

Max Activating Token Index: 162

Text #15

Max Range: 3.6528. Min Range: -3.6528

Max Act: 2.4219. Min Act: -0.0000

Data Index: 299935 (The Pile)

Max Activating Token Index: 847

Text #16

Max Range: 3.6528. Min Range: -3.6528

Max Act: 2.9806. Min Act: -0.0000

Data Index: 1230832 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 3.6528. Min Range: -3.6528

Max Act: 2.8030. Min Act: -0.0000

Data Index: 1589097 (The Pile)

Max Activating Token Index: 566

Text #18

Max Range: 3.6528. Min Range: -3.6528

Max Act: 2.7802. Min Act: -0.0000

Data Index: 849146 (The Pile)

Max Activating Token Index: 603

Text #19

Max Range: 3.6528. Min Range: -3.6528

Max Act: 2.4773. Min Act: -0.0000

Data Index: 879583 (The Pile)

Max Activating Token Index: 922