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

Dataset: The Pile

Neuron 2213 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: 0.9252. Min Range: -0.9252

Max Act: 0.9252. Min Act: -0.0000

Data Index: 1040364 (The Pile)

Max Activating Token Index: 487

Text #1

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1211118 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1369682 (The Pile)

Max Activating Token Index: 481

Text #3

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1163530 (The Pile)

Max Activating Token Index: 607

Text #4

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1463295 (The Pile)

Max Activating Token Index: 980

Text #5

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.5677. Min Act: -0.0000

Data Index: 1736049 (The Pile)

Max Activating Token Index: 834

Text #6

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.5436. Min Act: -0.0000

Data Index: 489671 (The Pile)

Max Activating Token Index: 331

Text #7

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1425118 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1170733 (The Pile)

Max Activating Token Index: 428

Text #9

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.5237. Min Act: -0.0000

Data Index: 440483 (The Pile)

Max Activating Token Index: 380

Text #10

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1240424 (The Pile)

Max Activating Token Index: 297

Text #11

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.4904. Min Act: -0.0000

Data Index: 1357207 (The Pile)

Max Activating Token Index: 440

Text #12

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.4695. Min Act: -0.0000

Data Index: 236950 (The Pile)

Max Activating Token Index: 765

Text #13

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1301852 (The Pile)

Max Activating Token Index: 290

Text #14

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1210153 (The Pile)

Max Activating Token Index: 438

Text #15

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.4766. Min Act: -0.0000

Data Index: 236533 (The Pile)

Max Activating Token Index: 725

Text #16

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.4409. Min Act: -0.0000

Data Index: 344276 (The Pile)

Max Activating Token Index: 925

Text #17

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.4169. Min Act: -0.0000

Data Index: 1593968 (The Pile)

Max Activating Token Index: 490

Text #18

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.4211. Min Act: -0.0000

Data Index: 1889519 (The Pile)

Max Activating Token Index: 166

Text #19

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.4129. Min Act: -0.0000

Data Index: 235497 (The Pile)

Max Activating Token Index: 810