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

Dataset: The Pile

Neuron 218 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1604. Min Act: -0.0000

Data Index: 1977737 (The Pile)

Max Activating Token Index: 268

Text #1

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1493. Min Act: -0.0000

Data Index: 747407 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1504. Min Act: -0.0000

Data Index: 936685 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1373. Min Act: -0.0000

Data Index: 980183 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1345. Min Act: -0.0000

Data Index: 1774024 (The Pile)

Max Activating Token Index: 630

Text #5

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1180927 (The Pile)

Max Activating Token Index: 854

Text #6

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1404. Min Act: -0.0000

Data Index: 549748 (The Pile)

Max Activating Token Index: 189

Text #7

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1322. Min Act: -0.0000

Data Index: 358181 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1232. Min Act: -0.0000

Data Index: 1713711 (The Pile)

Max Activating Token Index: 557

Text #9

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1177. Min Act: -0.0000

Data Index: 893984 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1204. Min Act: -0.0000

Data Index: 761979 (The Pile)

Max Activating Token Index: 665

Text #11

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1246. Min Act: -0.0000

Data Index: 475206 (The Pile)

Max Activating Token Index: 1006

Text #12

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1166. Min Act: -0.0000

Data Index: 503361 (The Pile)

Max Activating Token Index: 983

Text #13

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1234. Min Act: -0.0000

Data Index: 588527 (The Pile)

Max Activating Token Index: 713

Text #14

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1196. Min Act: -0.0000

Data Index: 107447 (The Pile)

Max Activating Token Index: 602

Text #15

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1237. Min Act: -0.0000

Data Index: 9932 (The Pile)

Max Activating Token Index: 498

Text #16

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1276. Min Act: -0.0000

Data Index: 892967 (The Pile)

Max Activating Token Index: 386

Text #17

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1191. Min Act: -0.0000

Data Index: 331479 (The Pile)

Max Activating Token Index: 85

Text #18

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1153. Min Act: -0.0000

Data Index: 556627 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 0.1604. Min Range: -0.1604

Max Act: 0.1152. Min Act: -0.0000

Data Index: 1223742 (The Pile)

Max Activating Token Index: 351