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

Dataset: The Pile

Neuron 4581 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.5621. Min Act: -0.0000

Data Index: 1010438 (The Pile)

Max Activating Token Index: 455

Text #1

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.3760. Min Act: -0.0000

Data Index: 582042 (The Pile)

Max Activating Token Index: 309

Text #2

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.3060. Min Act: -0.0000

Data Index: 1931490 (The Pile)

Max Activating Token Index: 116

Text #3

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.5398. Min Act: -0.0000

Data Index: 1833160 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.1778. Min Act: -0.0000

Data Index: 1786914 (The Pile)

Max Activating Token Index: 650

Text #5

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.1169. Min Act: -0.0000

Data Index: 994999 (The Pile)

Max Activating Token Index: 921

Text #6

Max Range: 1.5621. Min Range: -1.5621

Max Act: 0.8949. Min Act: -0.0000

Data Index: 931687 (The Pile)

Max Activating Token Index: 147

Text #7

Max Range: 1.5621. Min Range: -1.5621

Max Act: 0.8668. Min Act: -0.0000

Data Index: 777973 (The Pile)

Max Activating Token Index: 15

Text #8

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.0513. Min Act: -0.0000

Data Index: 1697194 (The Pile)

Max Activating Token Index: 432

Text #9

Max Range: 1.5621. Min Range: -1.5621

Max Act: 0.9448. Min Act: -0.0000

Data Index: 323435 (The Pile)

Max Activating Token Index: 67

Text #10

Max Range: 1.5621. Min Range: -1.5621

Max Act: 0.9456. Min Act: -0.0000

Data Index: 507176 (The Pile)

Max Activating Token Index: 250

Text #11

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.0255. Min Act: -0.0000

Data Index: 664179 (The Pile)

Max Activating Token Index: 648

Text #12

Max Range: 1.5621. Min Range: -1.5621

Max Act: 0.9403. Min Act: -0.0000

Data Index: 15349 (The Pile)

Max Activating Token Index: 122

Text #13

Max Range: 1.5621. Min Range: -1.5621

Max Act: 0.8519. Min Act: -0.0000

Data Index: 662565 (The Pile)

Max Activating Token Index: 92

Text #14

Max Range: 1.5621. Min Range: -1.5621

Max Act: 0.9277. Min Act: -0.0000

Data Index: 1240769 (The Pile)

Max Activating Token Index: 440

Text #15

Max Range: 1.5621. Min Range: -1.5621

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1727868 (The Pile)

Max Activating Token Index: 37

Text #16

Max Range: 1.5621. Min Range: -1.5621

Max Act: 0.8370. Min Act: -0.0000

Data Index: 346898 (The Pile)

Max Activating Token Index: 979

Text #17

Max Range: 1.5621. Min Range: -1.5621

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1236470 (The Pile)

Max Activating Token Index: 623

Text #18

Max Range: 1.5621. Min Range: -1.5621

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1872040 (The Pile)

Max Activating Token Index: 444

Text #19

Max Range: 1.5621. Min Range: -1.5621

Max Act: 0.8771. Min Act: -0.0000

Data Index: 1810600 (The Pile)

Max Activating Token Index: 872