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

Dataset: The Pile

Neuron 3982 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: 0.2365. Min Range: -0.2365

Max Act: 0.2365. Min Act: -0.0000

Data Index: 883078 (The Pile)

Max Activating Token Index: 925

Text #1

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1360615 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1668. Min Act: -0.0000

Data Index: 1677795 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1853012 (The Pile)

Max Activating Token Index: 715

Text #4

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1522. Min Act: -0.0000

Data Index: 370918 (The Pile)

Max Activating Token Index: 645

Text #5

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1514. Min Act: -0.0000

Data Index: 919204 (The Pile)

Max Activating Token Index: 953

Text #6

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1525. Min Act: -0.0000

Data Index: 670578 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1398. Min Act: -0.0000

Data Index: 724291 (The Pile)

Max Activating Token Index: 999

Text #8

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1394. Min Act: -0.0000

Data Index: 413768 (The Pile)

Max Activating Token Index: 999

Text #9

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1372. Min Act: -0.0000

Data Index: 13439 (The Pile)

Max Activating Token Index: 317

Text #10

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1318. Min Act: -0.0000

Data Index: 135230 (The Pile)

Max Activating Token Index: 420

Text #11

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1298. Min Act: -0.0000

Data Index: 296281 (The Pile)

Max Activating Token Index: 429

Text #12

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1401. Min Act: -0.0000

Data Index: 827252 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1260. Min Act: -0.0000

Data Index: 969074 (The Pile)

Max Activating Token Index: 945

Text #14

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1373. Min Act: -0.0000

Data Index: 779075 (The Pile)

Max Activating Token Index: 923

Text #15

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1368297 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1350. Min Act: -0.0000

Data Index: 902243 (The Pile)

Max Activating Token Index: 752

Text #17

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1372. Min Act: -0.0000

Data Index: 1738896 (The Pile)

Max Activating Token Index: 720

Text #18

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1395. Min Act: -0.0000

Data Index: 847462 (The Pile)

Max Activating Token Index: 782

Text #19

Max Range: 0.2365. Min Range: -0.2365

Max Act: 0.1335. Min Act: -0.0000

Data Index: 818784 (The Pile)

Max Activating Token Index: 551