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

Dataset: The Pile

Neuron 2312 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: 1.0710. Min Range: -1.0710

Max Act: 1.0710. Min Act: -0.0000

Data Index: 741920 (The Pile)

Max Activating Token Index: 504

Text #1

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1980799 (The Pile)

Max Activating Token Index: 473

Text #2

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.9137. Min Act: -0.0000

Data Index: 1617597 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1434318 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.9214. Min Act: -0.0000

Data Index: 1991907 (The Pile)

Max Activating Token Index: 299

Text #5

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8686. Min Act: -0.0000

Data Index: 264813 (The Pile)

Max Activating Token Index: 832

Text #6

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1740157 (The Pile)

Max Activating Token Index: 511

Text #7

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8677. Min Act: -0.0000

Data Index: 1472000 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8883. Min Act: -0.0000

Data Index: 738073 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1514672 (The Pile)

Max Activating Token Index: 522

Text #10

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8514. Min Act: -0.0000

Data Index: 82991 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8412. Min Act: -0.0000

Data Index: 627808 (The Pile)

Max Activating Token Index: 255

Text #12

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8142. Min Act: -0.0000

Data Index: 935861 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8335. Min Act: -0.0000

Data Index: 442616 (The Pile)

Max Activating Token Index: 458

Text #14

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1752624 (The Pile)

Max Activating Token Index: 116

Text #15

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1469121 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7954. Min Act: -0.0000

Data Index: 1081652 (The Pile)

Max Activating Token Index: 330

Text #17

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8157. Min Act: -0.0000

Data Index: 1136075 (The Pile)

Max Activating Token Index: 75

Text #18

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8499. Min Act: -0.0000

Data Index: 543699 (The Pile)

Max Activating Token Index: 894

Text #19

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1076614 (The Pile)

Max Activating Token Index: 798