Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1700 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1705. Min Act: -0.0000

Data Index: 1376722 (The Pile)

Max Activating Token Index: 686

Text #1

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1805. Min Act: -0.0000

Data Index: 423097 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1628. Min Act: -0.0000

Data Index: 591375 (The Pile)

Max Activating Token Index: 790

Text #3

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1576. Min Act: -0.0000

Data Index: 1233411 (The Pile)

Max Activating Token Index: 289

Text #4

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1316890 (The Pile)

Max Activating Token Index: 438

Text #5

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1379. Min Act: -0.0000

Data Index: 1384093 (The Pile)

Max Activating Token Index: 802

Text #6

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1329. Min Act: -0.0000

Data Index: 1331000 (The Pile)

Max Activating Token Index: 729

Text #7

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1531. Min Act: -0.0000

Data Index: 1535937 (The Pile)

Max Activating Token Index: 311

Text #8

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1332537 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1240216 (The Pile)

Max Activating Token Index: 299

Text #10

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1377. Min Act: -0.0000

Data Index: 591473 (The Pile)

Max Activating Token Index: 766

Text #11

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1376. Min Act: -0.0000

Data Index: 447449 (The Pile)

Max Activating Token Index: 619

Text #12

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1863124 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1433. Min Act: -0.0000

Data Index: 824129 (The Pile)

Max Activating Token Index: 94

Text #14

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1377. Min Act: -0.0000

Data Index: 1845460 (The Pile)

Max Activating Token Index: 558

Text #15

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1275. Min Act: -0.0000

Data Index: 130289 (The Pile)

Max Activating Token Index: 25

Text #16

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1404. Min Act: -0.0000

Data Index: 365080 (The Pile)

Max Activating Token Index: 196

Text #17

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1350. Min Act: -0.0000

Data Index: 66190 (The Pile)

Max Activating Token Index: 345

Text #18

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1297. Min Act: -0.0000

Data Index: 294924 (The Pile)

Max Activating Token Index: 924

Text #19

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1339. Min Act: -0.0000

Data Index: 92536 (The Pile)

Max Activating Token Index: 25