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

Dataset: The Pile

Neuron 4402 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1829. Min Range: -1.1829

Max Act: 1.1829. Min Act: -0.0000

Data Index: 569991 (The Pile)

Max Activating Token Index: 573

Text #1

Max Range: 1.1829. Min Range: -1.1829

Max Act: 1.0350. Min Act: -0.0000

Data Index: 1631471 (The Pile)

Max Activating Token Index: 946

Text #2

Max Range: 1.1829. Min Range: -1.1829

Max Act: 1.0066. Min Act: -0.0000

Data Index: 785535 (The Pile)

Max Activating Token Index: 807

Text #3

Max Range: 1.1829. Min Range: -1.1829

Max Act: 1.0874. Min Act: -0.0000

Data Index: 1871284 (The Pile)

Max Activating Token Index: 406

Text #4

Max Range: 1.1829. Min Range: -1.1829

Max Act: 1.0983. Min Act: -0.0000

Data Index: 327357 (The Pile)

Max Activating Token Index: 185

Text #5

Max Range: 1.1829. Min Range: -1.1829

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1734388 (The Pile)

Max Activating Token Index: 982

Text #6

Max Range: 1.1829. Min Range: -1.1829

Max Act: 1.0773. Min Act: -0.0000

Data Index: 841007 (The Pile)

Max Activating Token Index: 301

Text #7

Max Range: 1.1829. Min Range: -1.1829

Max Act: 1.1110. Min Act: -0.0000

Data Index: 1646627 (The Pile)

Max Activating Token Index: 945

Text #8

Max Range: 1.1829. Min Range: -1.1829

Max Act: 1.0076. Min Act: -0.0000

Data Index: 833941 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 1.1829. Min Range: -1.1829

Max Act: 1.0573. Min Act: -0.0000

Data Index: 1168446 (The Pile)

Max Activating Token Index: 140

Text #10

Max Range: 1.1829. Min Range: -1.1829

Max Act: 0.9981. Min Act: -0.0000

Data Index: 505026 (The Pile)

Max Activating Token Index: 343

Text #11

Max Range: 1.1829. Min Range: -1.1829

Max Act: 0.9974. Min Act: -0.0000

Data Index: 422706 (The Pile)

Max Activating Token Index: 267

Text #12

Max Range: 1.1829. Min Range: -1.1829

Max Act: 0.9390. Min Act: -0.0000

Data Index: 1434322 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 1.1829. Min Range: -1.1829

Max Act: 1.0138. Min Act: -0.0000

Data Index: 1302318 (The Pile)

Max Activating Token Index: 204

Text #14

Max Range: 1.1829. Min Range: -1.1829

Max Act: 1.0110. Min Act: -0.0000

Data Index: 618686 (The Pile)

Max Activating Token Index: 481

Text #15

Max Range: 1.1829. Min Range: -1.1829

Max Act: 0.9521. Min Act: -0.0000

Data Index: 889552 (The Pile)

Max Activating Token Index: 807

Text #16

Max Range: 1.1829. Min Range: -1.1829

Max Act: 0.9874. Min Act: -0.0000

Data Index: 1259242 (The Pile)

Max Activating Token Index: 1022

Text #17

Max Range: 1.1829. Min Range: -1.1829

Max Act: 0.9482. Min Act: -0.0000

Data Index: 1235120 (The Pile)

Max Activating Token Index: 368

Text #18

Max Range: 1.1829. Min Range: -1.1829

Max Act: 0.9490. Min Act: -0.0000

Data Index: 525217 (The Pile)

Max Activating Token Index: 251

Text #19

Max Range: 1.1829. Min Range: -1.1829

Max Act: 1.0068. Min Act: -0.0000

Data Index: 571014 (The Pile)

Max Activating Token Index: 128