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

Dataset: The Pile

Neuron 2891 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.9305. Min Act: -0.0000

Data Index: 61703 (The Pile)

Max Activating Token Index: 524

Text #1

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.6766. Min Act: -0.0000

Data Index: 473429 (The Pile)

Max Activating Token Index: 966

Text #2

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.6244. Min Act: -0.0000

Data Index: 637613 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1587172 (The Pile)

Max Activating Token Index: 299

Text #4

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1665365 (The Pile)

Max Activating Token Index: 275

Text #5

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1737991 (The Pile)

Max Activating Token Index: 59

Text #6

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1796066 (The Pile)

Max Activating Token Index: 1010

Text #7

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.4815. Min Act: -0.0000

Data Index: 83219 (The Pile)

Max Activating Token Index: 398

Text #8

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.4702. Min Act: -0.0000

Data Index: 1983582 (The Pile)

Max Activating Token Index: 864

Text #9

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.4486. Min Act: -0.0000

Data Index: 319410 (The Pile)

Max Activating Token Index: 45

Text #10

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.4265. Min Act: -0.0000

Data Index: 254335 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1564924 (The Pile)

Max Activating Token Index: 613

Text #12

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.4363. Min Act: -0.0000

Data Index: 124915 (The Pile)

Max Activating Token Index: 511

Text #13

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.3934. Min Act: -0.0000

Data Index: 42354 (The Pile)

Max Activating Token Index: 981

Text #14

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.3737. Min Act: -0.0000

Data Index: 1970943 (The Pile)

Max Activating Token Index: 81

Text #15

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.4299. Min Act: -0.0000

Data Index: 956459 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.3925. Min Act: -0.0000

Data Index: 178965 (The Pile)

Max Activating Token Index: 440

Text #17

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.3882. Min Act: -0.0000

Data Index: 370742 (The Pile)

Max Activating Token Index: 91

Text #18

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1160744 (The Pile)

Max Activating Token Index: 461

Text #19

Max Range: 0.9305. Min Range: -0.9305

Max Act: 0.3977. Min Act: -0.0000

Data Index: 1475566 (The Pile)

Max Activating Token Index: 827