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

Dataset: The Pile

Neuron 3460 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4756. Min Range: -1.4756

Max Act: 1.4756. Min Act: -0.0000

Data Index: 1116882 (The Pile)

Max Activating Token Index: 213

Text #1

Max Range: 1.4756. Min Range: -1.4756

Max Act: 1.0777. Min Act: -0.0000

Data Index: 805361 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 1.4756. Min Range: -1.4756

Max Act: 1.0415. Min Act: -0.0000

Data Index: 1411614 (The Pile)

Max Activating Token Index: 399

Text #3

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.9969. Min Act: -0.0000

Data Index: 343412 (The Pile)

Max Activating Token Index: 426

Text #4

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1393104 (The Pile)

Max Activating Token Index: 337

Text #5

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.8841. Min Act: -0.0000

Data Index: 979741 (The Pile)

Max Activating Token Index: 449

Text #6

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.7853. Min Act: -0.0000

Data Index: 471464 (The Pile)

Max Activating Token Index: 557

Text #7

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1570823 (The Pile)

Max Activating Token Index: 601

Text #8

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.7667. Min Act: 0.0000

Data Index: 426717 (The Pile)

Max Activating Token Index: 836

Text #9

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1946817 (The Pile)

Max Activating Token Index: 373

Text #10

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.7839. Min Act: -0.0000

Data Index: 413042 (The Pile)

Max Activating Token Index: 1020

Text #11

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.7522. Min Act: -0.0000

Data Index: 223984 (The Pile)

Max Activating Token Index: 904

Text #12

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1163199 (The Pile)

Max Activating Token Index: 974

Text #13

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.6826. Min Act: -0.0000

Data Index: 1848308 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.6820. Min Act: -0.0000

Data Index: 355672 (The Pile)

Max Activating Token Index: 845

Text #15

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.5193. Min Act: -0.0000

Data Index: 187108 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.6663. Min Act: -0.0000

Data Index: 1686076 (The Pile)

Max Activating Token Index: 616

Text #17

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.6527. Min Act: -0.0000

Data Index: 787430 (The Pile)

Max Activating Token Index: 824

Text #18

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1658814 (The Pile)

Max Activating Token Index: 605

Text #19

Max Range: 1.4756. Min Range: -1.4756

Max Act: 0.5876. Min Act: -0.0000

Data Index: 129369 (The Pile)

Max Activating Token Index: 241