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

Dataset: The Pile

Neuron 3305 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1549. Min Act: 0.0000

Data Index: 1069726 (The Pile)

Max Activating Token Index: 81

Text #1

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1618182 (The Pile)

Max Activating Token Index: 278

Text #2

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1483. Min Act: 0.0000

Data Index: 1757533 (The Pile)

Max Activating Token Index: 343

Text #3

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1411. Min Act: -0.0000

Data Index: 1854303 (The Pile)

Max Activating Token Index: 211

Text #4

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1334172 (The Pile)

Max Activating Token Index: 429

Text #5

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1388. Min Act: -0.0000

Data Index: 1117026 (The Pile)

Max Activating Token Index: 273

Text #6

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1462646 (The Pile)

Max Activating Token Index: 731

Text #7

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1353. Min Act: -0.0000

Data Index: 1302787 (The Pile)

Max Activating Token Index: 344

Text #8

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1754479 (The Pile)

Max Activating Token Index: 799

Text #9

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1262. Min Act: -0.0000

Data Index: 780511 (The Pile)

Max Activating Token Index: 446

Text #10

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1335252 (The Pile)

Max Activating Token Index: 695

Text #11

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1392. Min Act: -0.0000

Data Index: 467965 (The Pile)

Max Activating Token Index: 604

Text #12

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1732781 (The Pile)

Max Activating Token Index: 276

Text #13

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1387. Min Act: -0.0000

Data Index: 500582 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1313. Min Act: -0.0000

Data Index: 883624 (The Pile)

Max Activating Token Index: 533

Text #15

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1397. Min Act: -0.0000

Data Index: 767068 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1289. Min Act: -0.0000

Data Index: 524326 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1269. Min Act: -0.0000

Data Index: 684066 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1003986 (The Pile)

Max Activating Token Index: 713

Text #19

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1386. Min Act: 0.0000

Data Index: 1594062 (The Pile)

Max Activating Token Index: 34