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

Dataset: The Pile

Neuron 1975 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: 0.2890. Min Range: -0.2890

Max Act: 0.2890. Min Act: -0.0000

Data Index: 13789 (The Pile)

Max Activating Token Index: 160

Text #1

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1632. Min Act: -0.0000

Data Index: 713865 (The Pile)

Max Activating Token Index: 240

Text #2

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1646. Min Act: -0.0000

Data Index: 9834 (The Pile)

Max Activating Token Index: 325

Text #3

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1555. Min Act: -0.0000

Data Index: 535366 (The Pile)

Max Activating Token Index: 240

Text #4

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1403418 (The Pile)

Max Activating Token Index: 343

Text #5

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1909252 (The Pile)

Max Activating Token Index: 783

Text #6

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1511. Min Act: -0.0000

Data Index: 210842 (The Pile)

Max Activating Token Index: 459

Text #7

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1922744 (The Pile)

Max Activating Token Index: 413

Text #8

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1387. Min Act: -0.0000

Data Index: 1610219 (The Pile)

Max Activating Token Index: 448

Text #9

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1428. Min Act: -0.0000

Data Index: 1094030 (The Pile)

Max Activating Token Index: 993

Text #10

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1281. Min Act: -0.0000

Data Index: 952728 (The Pile)

Max Activating Token Index: 625

Text #11

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1492420 (The Pile)

Max Activating Token Index: 295

Text #12

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1246. Min Act: -0.0000

Data Index: 1395615 (The Pile)

Max Activating Token Index: 65

Text #13

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1293. Min Act: -0.0000

Data Index: 408707 (The Pile)

Max Activating Token Index: 936

Text #14

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1274. Min Act: -0.0000

Data Index: 1007156 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1329. Min Act: -0.0000

Data Index: 1217339 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1276. Min Act: -0.0000

Data Index: 998616 (The Pile)

Max Activating Token Index: 22

Text #17

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1065. Min Act: -0.0000

Data Index: 636235 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1338. Min Act: -0.0000

Data Index: 842216 (The Pile)

Max Activating Token Index: 384

Text #19

Max Range: 0.2890. Min Range: -0.2890

Max Act: 0.1210. Min Act: -0.0000

Data Index: 475553 (The Pile)

Max Activating Token Index: 560