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

Dataset: The Pile

Neuron 2523 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1669345 (The Pile)

Max Activating Token Index: 671

Text #1

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1471. Min Act: -0.0000

Data Index: 808223 (The Pile)

Max Activating Token Index: 409

Text #2

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1362103 (The Pile)

Max Activating Token Index: 827

Text #3

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1422. Min Act: -0.0000

Data Index: 658168 (The Pile)

Max Activating Token Index: 888

Text #4

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1574. Min Act: -0.0000

Data Index: 95699 (The Pile)

Max Activating Token Index: 541

Text #5

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1413. Min Act: -0.0000

Data Index: 152666 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1662958 (The Pile)

Max Activating Token Index: 1013

Text #7

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1462. Min Act: -0.0000

Data Index: 17323 (The Pile)

Max Activating Token Index: 937

Text #8

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1401. Min Act: -0.0000

Data Index: 1784569 (The Pile)

Max Activating Token Index: 867

Text #9

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1382. Min Act: -0.0000

Data Index: 795336 (The Pile)

Max Activating Token Index: 946

Text #10

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1351. Min Act: -0.0000

Data Index: 762167 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1292. Min Act: -0.0000

Data Index: 626860 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1344740 (The Pile)

Max Activating Token Index: 65

Text #13

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1387. Min Act: -0.0000

Data Index: 132065 (The Pile)

Max Activating Token Index: 519

Text #14

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1330. Min Act: -0.0000

Data Index: 536258 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1377210 (The Pile)

Max Activating Token Index: 938

Text #16

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1319. Min Act: -0.0000

Data Index: 848136 (The Pile)

Max Activating Token Index: 544

Text #17

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1317. Min Act: -0.0000

Data Index: 1738088 (The Pile)

Max Activating Token Index: 272

Text #18

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1407. Min Act: -0.0000

Data Index: 1097414 (The Pile)

Max Activating Token Index: 665

Text #19

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1237. Min Act: -0.0000

Data Index: 417145 (The Pile)

Max Activating Token Index: 1020