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

Dataset: The Pile

Neuron 3750 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: 0.2514. Min Range: -0.2514

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1435366 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.2024. Min Act: -0.0000

Data Index: 229748 (The Pile)

Max Activating Token Index: 369

Text #2

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1564. Min Act: -0.0000

Data Index: 97542 (The Pile)

Max Activating Token Index: 618

Text #3

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1519. Min Act: -0.0000

Data Index: 1116087 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1502. Min Act: -0.0000

Data Index: 996090 (The Pile)

Max Activating Token Index: 259

Text #5

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1468. Min Act: -0.0000

Data Index: 427678 (The Pile)

Max Activating Token Index: 245

Text #6

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1541. Min Act: -0.0000

Data Index: 1441980 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1584. Min Act: -0.0000

Data Index: 594087 (The Pile)

Max Activating Token Index: 36

Text #8

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1717. Min Act: -0.0000

Data Index: 448245 (The Pile)

Max Activating Token Index: 616

Text #9

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1373. Min Act: -0.0000

Data Index: 370355 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1355. Min Act: -0.0000

Data Index: 655232 (The Pile)

Max Activating Token Index: 188

Text #11

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1294. Min Act: -0.0000

Data Index: 1626690 (The Pile)

Max Activating Token Index: 513

Text #12

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1396. Min Act: -0.0000

Data Index: 1169975 (The Pile)

Max Activating Token Index: 802

Text #13

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1641987 (The Pile)

Max Activating Token Index: 225

Text #14

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1418. Min Act: -0.0000

Data Index: 370588 (The Pile)

Max Activating Token Index: 832

Text #15

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1403. Min Act: -0.0000

Data Index: 1781831 (The Pile)

Max Activating Token Index: 423

Text #16

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1385. Min Act: -0.0000

Data Index: 501061 (The Pile)

Max Activating Token Index: 480

Text #17

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.0814. Min Act: -0.0000

Data Index: 1222672 (The Pile)

Max Activating Token Index: 766

Text #18

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1190. Min Act: -0.0000

Data Index: 1941163 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 0.2514. Min Range: -0.2514

Max Act: 0.1590. Min Act: -0.0000

Data Index: 790112 (The Pile)

Max Activating Token Index: 699