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

Dataset: The Pile

Neuron 4031 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.9316. Min Act: -0.0000

Data Index: 675124 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1718832 (The Pile)

Max Activating Token Index: 461

Text #2

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1532826 (The Pile)

Max Activating Token Index: 606

Text #3

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1667014 (The Pile)

Max Activating Token Index: 169

Text #4

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.8350. Min Act: -0.0000

Data Index: 1882460 (The Pile)

Max Activating Token Index: 729

Text #5

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.7674. Min Act: -0.0000

Data Index: 115841 (The Pile)

Max Activating Token Index: 660

Text #6

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.7006. Min Act: -0.0000

Data Index: 582738 (The Pile)

Max Activating Token Index: 667

Text #7

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.8353. Min Act: -0.0000

Data Index: 944832 (The Pile)

Max Activating Token Index: 830

Text #8

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1470961 (The Pile)

Max Activating Token Index: 439

Text #9

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.8284. Min Act: -0.0000

Data Index: 230817 (The Pile)

Max Activating Token Index: 482

Text #10

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1010856 (The Pile)

Max Activating Token Index: 754

Text #11

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1054111 (The Pile)

Max Activating Token Index: 607

Text #12

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.8182. Min Act: -0.0000

Data Index: 166249 (The Pile)

Max Activating Token Index: 838

Text #13

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1255874 (The Pile)

Max Activating Token Index: 319

Text #14

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.7662. Min Act: -0.0000

Data Index: 805523 (The Pile)

Max Activating Token Index: 504

Text #15

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.8040. Min Act: -0.0000

Data Index: 293551 (The Pile)

Max Activating Token Index: 394

Text #16

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1490042 (The Pile)

Max Activating Token Index: 70

Text #17

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.7960. Min Act: -0.0000

Data Index: 413906 (The Pile)

Max Activating Token Index: 974

Text #18

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.8032. Min Act: -0.0000

Data Index: 239770 (The Pile)

Max Activating Token Index: 18

Text #19

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.8048. Min Act: -0.0000

Data Index: 1733786 (The Pile)

Max Activating Token Index: 217