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

Dataset: The Pile

Neuron 2551 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: 0.2103. Min Range: -0.2103

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1176398 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1037517 (The Pile)

Max Activating Token Index: 682

Text #2

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1801. Min Act: -0.0000

Data Index: 232425 (The Pile)

Max Activating Token Index: 725

Text #3

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1675. Min Act: -0.0000

Data Index: 563502 (The Pile)

Max Activating Token Index: 272

Text #4

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1701. Min Act: -0.0000

Data Index: 1423234 (The Pile)

Max Activating Token Index: 241

Text #5

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1619. Min Act: -0.0000

Data Index: 553681 (The Pile)

Max Activating Token Index: 431

Text #6

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1566. Min Act: -0.0000

Data Index: 1268787 (The Pile)

Max Activating Token Index: 196

Text #7

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1474. Min Act: -0.0000

Data Index: 195376 (The Pile)

Max Activating Token Index: 631

Text #8

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1608. Min Act: -0.0000

Data Index: 1866050 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1630. Min Act: -0.0000

Data Index: 1393072 (The Pile)

Max Activating Token Index: 1000

Text #10

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1479. Min Act: -0.0000

Data Index: 1381142 (The Pile)

Max Activating Token Index: 237

Text #11

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1826800 (The Pile)

Max Activating Token Index: 805

Text #12

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1727655 (The Pile)

Max Activating Token Index: 617

Text #13

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1493. Min Act: -0.0000

Data Index: 388337 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1413. Min Act: -0.0000

Data Index: 543877 (The Pile)

Max Activating Token Index: 214

Text #15

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1444. Min Act: -0.0000

Data Index: 715861 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1672542 (The Pile)

Max Activating Token Index: 342

Text #17

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1094184 (The Pile)

Max Activating Token Index: 397

Text #18

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1572263 (The Pile)

Max Activating Token Index: 200

Text #19

Max Range: 0.2103. Min Range: -0.2103

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1497947 (The Pile)

Max Activating Token Index: 828