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

Dataset: The Pile

Neuron 3739 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.4304. Min Act: -0.0000

Data Index: 621348 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.3178. Min Act: -0.0000

Data Index: 1798743 (The Pile)

Max Activating Token Index: 792

Text #2

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.2856. Min Act: -0.0000

Data Index: 1336683 (The Pile)

Max Activating Token Index: 910

Text #3

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.4351. Min Act: -0.0000

Data Index: 415723 (The Pile)

Max Activating Token Index: 367

Text #4

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.3814. Min Act: -0.0000

Data Index: 391119 (The Pile)

Max Activating Token Index: 679

Text #5

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.1051. Min Act: -0.0000

Data Index: 295842 (The Pile)

Max Activating Token Index: 651

Text #6

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.2548. Min Act: -0.0000

Data Index: 1760521 (The Pile)

Max Activating Token Index: 820

Text #7

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.1783. Min Act: -0.0000

Data Index: 768996 (The Pile)

Max Activating Token Index: 229

Text #8

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.2353. Min Act: -0.0000

Data Index: 126360 (The Pile)

Max Activating Token Index: 820

Text #9

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.2039. Min Act: -0.0000

Data Index: 1464431 (The Pile)

Max Activating Token Index: 795

Text #10

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.1723. Min Act: -0.0000

Data Index: 708418 (The Pile)

Max Activating Token Index: 427

Text #11

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.1589. Min Act: -0.0000

Data Index: 1248515 (The Pile)

Max Activating Token Index: 847

Text #12

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.1570. Min Act: -0.0000

Data Index: 1538792 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1119332 (The Pile)

Max Activating Token Index: 298

Text #14

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.1354. Min Act: -0.0000

Data Index: 643260 (The Pile)

Max Activating Token Index: 512

Text #15

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.1124. Min Act: -0.0000

Data Index: 615213 (The Pile)

Max Activating Token Index: 472

Text #16

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.0896. Min Act: -0.0000

Data Index: 578128 (The Pile)

Max Activating Token Index: 479

Text #17

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.1041. Min Act: -0.0000

Data Index: 757853 (The Pile)

Max Activating Token Index: 287

Text #18

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.0406. Min Act: -0.0000

Data Index: 1702063 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 1.4351. Min Range: -1.4351

Max Act: 1.1307. Min Act: -0.0000

Data Index: 1940250 (The Pile)

Max Activating Token Index: 789