Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2264 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.2355. Min Act: -0.0001

Data Index: 1786562 (The Pile)

Max Activating Token Index: 652

Text #1

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.2091. Min Act: -0.0000

Data Index: 1969338 (The Pile)

Max Activating Token Index: 427

Text #2

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1099035 (The Pile)

Max Activating Token Index: 392

Text #3

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1973. Min Act: -0.0000

Data Index: 1200976 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1490. Min Act: -0.0000

Data Index: 757595 (The Pile)

Max Activating Token Index: 848

Text #5

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1996. Min Act: -0.0000

Data Index: 763174 (The Pile)

Max Activating Token Index: 803

Text #6

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.2053. Min Act: -0.0000

Data Index: 204344 (The Pile)

Max Activating Token Index: 493

Text #7

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1804. Min Act: -0.0000

Data Index: 1653322 (The Pile)

Max Activating Token Index: 355

Text #8

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1642. Min Act: -0.0000

Data Index: 591227 (The Pile)

Max Activating Token Index: 235

Text #9

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1760. Min Act: -0.0000

Data Index: 323575 (The Pile)

Max Activating Token Index: 158

Text #10

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1658. Min Act: -0.0000

Data Index: 1339539 (The Pile)

Max Activating Token Index: 590

Text #11

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1613791 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1589. Min Act: -0.0000

Data Index: 1244354 (The Pile)

Max Activating Token Index: 653

Text #13

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1912825 (The Pile)

Max Activating Token Index: 528

Text #14

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1656862 (The Pile)

Max Activating Token Index: 512

Text #15

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1509. Min Act: -0.0000

Data Index: 1436851 (The Pile)

Max Activating Token Index: 332

Text #16

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1555. Min Act: -0.0000

Data Index: 641225 (The Pile)

Max Activating Token Index: 436

Text #17

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1493. Min Act: -0.0000

Data Index: 222028 (The Pile)

Max Activating Token Index: 990

Text #18

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1474. Min Act: -0.0000

Data Index: 401297 (The Pile)

Max Activating Token Index: 509

Text #19

Max Range: 0.2355. Min Range: -0.2355

Max Act: 0.1008. Min Act: -0.0000

Data Index: 787356 (The Pile)

Max Activating Token Index: 122