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

Dataset: The Pile

Neuron 316 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: 0.2511. Min Range: -0.2511

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1283543 (The Pile)

Max Activating Token Index: 789

Text #1

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2218. Min Act: -0.0000

Data Index: 751069 (The Pile)

Max Activating Token Index: 594

Text #2

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2316. Min Act: -0.0000

Data Index: 384580 (The Pile)

Max Activating Token Index: 812

Text #3

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1718959 (The Pile)

Max Activating Token Index: 426

Text #4

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2128. Min Act: -0.0000

Data Index: 1338856 (The Pile)

Max Activating Token Index: 440

Text #5

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1852. Min Act: -0.0000

Data Index: 306542 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1629. Min Act: -0.0000

Data Index: 1824787 (The Pile)

Max Activating Token Index: 474

Text #7

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1568. Min Act: -0.0000

Data Index: 1546491 (The Pile)

Max Activating Token Index: 490

Text #8

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1637. Min Act: -0.0000

Data Index: 1629077 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1490. Min Act: -0.0000

Data Index: 652116 (The Pile)

Max Activating Token Index: 287

Text #10

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1577. Min Act: -0.0000

Data Index: 3897 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1608. Min Act: -0.0000

Data Index: 1488341 (The Pile)

Max Activating Token Index: 489

Text #12

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1566. Min Act: -0.0000

Data Index: 783752 (The Pile)

Max Activating Token Index: 632

Text #13

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1516221 (The Pile)

Max Activating Token Index: 563

Text #14

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1305037 (The Pile)

Max Activating Token Index: 253

Text #15

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1613. Min Act: -0.0000

Data Index: 989291 (The Pile)

Max Activating Token Index: 338

Text #16

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1400. Min Act: -0.0000

Data Index: 1602263 (The Pile)

Max Activating Token Index: 453

Text #17

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1106226 (The Pile)

Max Activating Token Index: 550

Text #18

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1363. Min Act: -0.0000

Data Index: 90222 (The Pile)

Max Activating Token Index: 387

Text #19

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1536. Min Act: -0.0000

Data Index: 118391 (The Pile)

Max Activating Token Index: 611