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

Dataset: The Pile

Neuron 3196 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: 4.3301. Min Range: -4.3301

Max Act: 4.3301. Min Act: -0.0000

Data Index: 166250 (The Pile)

Max Activating Token Index: 903

Text #1

Max Range: 4.3301. Min Range: -4.3301

Max Act: 3.9193. Min Act: -0.0000

Data Index: 1413438 (The Pile)

Max Activating Token Index: 360

Text #2

Max Range: 4.3301. Min Range: -4.3301

Max Act: 3.4679. Min Act: -0.0000

Data Index: 1357478 (The Pile)

Max Activating Token Index: 978

Text #3

Max Range: 4.3301. Min Range: -4.3301

Max Act: 3.2263. Min Act: -0.0000

Data Index: 869293 (The Pile)

Max Activating Token Index: 939

Text #4

Max Range: 4.3301. Min Range: -4.3301

Max Act: 3.3600. Min Act: -0.0000

Data Index: 921810 (The Pile)

Max Activating Token Index: 857

Text #5

Max Range: 4.3301. Min Range: -4.3301

Max Act: 3.3350. Min Act: -0.0000

Data Index: 242371 (The Pile)

Max Activating Token Index: 367

Text #6

Max Range: 4.3301. Min Range: -4.3301

Max Act: 3.1721. Min Act: -0.0000

Data Index: 1101002 (The Pile)

Max Activating Token Index: 671

Text #7

Max Range: 4.3301. Min Range: -4.3301

Max Act: 3.1324. Min Act: -0.0000

Data Index: 1307505 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 4.3301. Min Range: -4.3301

Max Act: 3.1047. Min Act: -0.0000

Data Index: 1598950 (The Pile)

Max Activating Token Index: 492

Text #9

Max Range: 4.3301. Min Range: -4.3301

Max Act: 3.2640. Min Act: -0.0000

Data Index: 312357 (The Pile)

Max Activating Token Index: 441

Text #10

Max Range: 4.3301. Min Range: -4.3301

Max Act: 3.2203. Min Act: -0.0000

Data Index: 1670647 (The Pile)

Max Activating Token Index: 683

Text #11

Max Range: 4.3301. Min Range: -4.3301

Max Act: 3.0645. Min Act: -0.0000

Data Index: 267496 (The Pile)

Max Activating Token Index: 461

Text #12

Max Range: 4.3301. Min Range: -4.3301

Max Act: 3.3588. Min Act: -0.0000

Data Index: 1246390 (The Pile)

Max Activating Token Index: 307

Text #13

Max Range: 4.3301. Min Range: -4.3301

Max Act: 3.1741. Min Act: -0.0000

Data Index: 1429749 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 4.3301. Min Range: -4.3301

Max Act: 3.2979. Min Act: -0.0000

Data Index: 1147666 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 4.3301. Min Range: -4.3301

Max Act: 3.1370. Min Act: -0.0000

Data Index: 498924 (The Pile)

Max Activating Token Index: 779

Text #16

Max Range: 4.3301. Min Range: -4.3301

Max Act: 3.3230. Min Act: -0.0000

Data Index: 1554165 (The Pile)

Max Activating Token Index: 393

Text #17

Max Range: 4.3301. Min Range: -4.3301

Max Act: 3.1361. Min Act: -0.0000

Data Index: 343758 (The Pile)

Max Activating Token Index: 700

Text #18

Max Range: 4.3301. Min Range: -4.3301

Max Act: 2.9602. Min Act: -0.0000

Data Index: 659447 (The Pile)

Max Activating Token Index: 581

Text #19

Max Range: 4.3301. Min Range: -4.3301

Max Act: 2.9029. Min Act: -0.0000

Data Index: 1286759 (The Pile)

Max Activating Token Index: 518