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

Dataset: The Pile

Neuron 2249 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0519. Min Range: -1.0519

Max Act: 1.0011. Min Act: -0.0000

Data Index: 1117497 (The Pile)

Max Activating Token Index: 402

Text #1

Max Range: 1.0519. Min Range: -1.0519

Max Act: 1.0519. Min Act: -0.0000

Data Index: 268523 (The Pile)

Max Activating Token Index: 388

Text #2

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.9358. Min Act: -0.0000

Data Index: 240032 (The Pile)

Max Activating Token Index: 205

Text #3

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1717991 (The Pile)

Max Activating Token Index: 409

Text #4

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.8936. Min Act: 0.0000

Data Index: 1859967 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.7770. Min Act: -0.0000

Data Index: 211439 (The Pile)

Max Activating Token Index: 527

Text #6

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.7775. Min Act: -0.0000

Data Index: 1160725 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1372461 (The Pile)

Max Activating Token Index: 697

Text #8

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.7758. Min Act: -0.0000

Data Index: 219683 (The Pile)

Max Activating Token Index: 468

Text #9

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.7637. Min Act: -0.0000

Data Index: 1769492 (The Pile)

Max Activating Token Index: 491

Text #10

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.7298. Min Act: -0.0000

Data Index: 355216 (The Pile)

Max Activating Token Index: 850

Text #11

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.7047. Min Act: -0.0000

Data Index: 979983 (The Pile)

Max Activating Token Index: 889

Text #12

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1936396 (The Pile)

Max Activating Token Index: 506

Text #13

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.6837. Min Act: -0.0000

Data Index: 1686733 (The Pile)

Max Activating Token Index: 398

Text #14

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1149856 (The Pile)

Max Activating Token Index: 706

Text #15

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.6533. Min Act: -0.0000

Data Index: 288539 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.7000. Min Act: -0.0000

Data Index: 963381 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.6827. Min Act: -0.0000

Data Index: 466773 (The Pile)

Max Activating Token Index: 361

Text #18

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.6624. Min Act: -0.0000

Data Index: 848105 (The Pile)

Max Activating Token Index: 478

Text #19

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1230746 (The Pile)

Max Activating Token Index: 277