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

Dataset: The Pile

Neuron 677 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: 1.0243. Min Range: -1.0243

Max Act: 1.0243. Min Act: -0.0000

Data Index: 1682512 (The Pile)

Max Activating Token Index: 290

Text #1

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.9328. Min Act: -0.0000

Data Index: 1589565 (The Pile)

Max Activating Token Index: 708

Text #2

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1361767 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1231446 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1030050 (The Pile)

Max Activating Token Index: 910

Text #5

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1937478 (The Pile)

Max Activating Token Index: 456

Text #6

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6343. Min Act: -0.0000

Data Index: 33834 (The Pile)

Max Activating Token Index: 150

Text #7

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6700. Min Act: -0.0000

Data Index: 183746 (The Pile)

Max Activating Token Index: 118

Text #8

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1601283 (The Pile)

Max Activating Token Index: 265

Text #9

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1259400 (The Pile)

Max Activating Token Index: 444

Text #10

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.5813. Min Act: -0.0000

Data Index: 1291366 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1806476 (The Pile)

Max Activating Token Index: 52

Text #12

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.5864. Min Act: -0.0000

Data Index: 269572 (The Pile)

Max Activating Token Index: 509

Text #13

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.5449. Min Act: -0.0000

Data Index: 78725 (The Pile)

Max Activating Token Index: 512

Text #14

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.4683. Min Act: -0.0000

Data Index: 412283 (The Pile)

Max Activating Token Index: 819

Text #15

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.5448. Min Act: -0.0000

Data Index: 339854 (The Pile)

Max Activating Token Index: 775

Text #16

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.5442. Min Act: -0.0000

Data Index: 1619188 (The Pile)

Max Activating Token Index: 367

Text #17

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.5402. Min Act: -0.0000

Data Index: 167982 (The Pile)

Max Activating Token Index: 416

Text #18

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1426810 (The Pile)

Max Activating Token Index: 424

Text #19

Max Range: 1.0243. Min Range: -1.0243

Max Act: 0.5327. Min Act: -0.0000

Data Index: 231602 (The Pile)

Max Activating Token Index: 685