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

Dataset: The Pile

Neuron 2866 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: 1.0065. Min Range: -1.0065

Max Act: 1.0065. Min Act: -0.0000

Data Index: 1935898 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.9395. Min Act: -0.0000

Data Index: 1305532 (The Pile)

Max Activating Token Index: 414

Text #2

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1106783 (The Pile)

Max Activating Token Index: 316

Text #3

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.7389. Min Act: -0.0000

Data Index: 383925 (The Pile)

Max Activating Token Index: 159

Text #4

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1502405 (The Pile)

Max Activating Token Index: 174

Text #5

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1835029 (The Pile)

Max Activating Token Index: 278

Text #6

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.5785. Min Act: 0.0000

Data Index: 1828100 (The Pile)

Max Activating Token Index: 127

Text #7

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.5761. Min Act: -0.0000

Data Index: 633339 (The Pile)

Max Activating Token Index: 762

Text #8

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1039810 (The Pile)

Max Activating Token Index: 817

Text #9

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.6068. Min Act: 0.0000

Data Index: 100919 (The Pile)

Max Activating Token Index: 692

Text #10

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.5382. Min Act: -0.0000

Data Index: 1137015 (The Pile)

Max Activating Token Index: 46

Text #11

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1394429 (The Pile)

Max Activating Token Index: 689

Text #12

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.5647. Min Act: -0.0000

Data Index: 819423 (The Pile)

Max Activating Token Index: 161

Text #13

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.5170. Min Act: -0.0000

Data Index: 631164 (The Pile)

Max Activating Token Index: 328

Text #14

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.5782. Min Act: -0.0000

Data Index: 292091 (The Pile)

Max Activating Token Index: 488

Text #15

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.5369. Min Act: -0.0000

Data Index: 529180 (The Pile)

Max Activating Token Index: 148

Text #16

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1536791 (The Pile)

Max Activating Token Index: 648

Text #17

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1731742 (The Pile)

Max Activating Token Index: 392

Text #18

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1688373 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 1.0065. Min Range: -1.0065

Max Act: 0.5331. Min Act: -0.0000

Data Index: 570051 (The Pile)

Max Activating Token Index: 258