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

Dataset: The Pile

Neuron 2358 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: 4.2498. Min Range: -4.2498

Max Act: 4.2498. Min Act: -0.0000

Data Index: 1248548 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 4.2498. Min Range: -4.2498

Max Act: 4.0818. Min Act: -0.0000

Data Index: 246950 (The Pile)

Max Activating Token Index: 942

Text #2

Max Range: 4.2498. Min Range: -4.2498

Max Act: 3.8025. Min Act: -0.0000

Data Index: 1912583 (The Pile)

Max Activating Token Index: 150

Text #3

Max Range: 4.2498. Min Range: -4.2498

Max Act: 3.7824. Min Act: -0.0000

Data Index: 63760 (The Pile)

Max Activating Token Index: 367

Text #4

Max Range: 4.2498. Min Range: -4.2498

Max Act: 3.9335. Min Act: -0.0000

Data Index: 1211659 (The Pile)

Max Activating Token Index: 643

Text #5

Max Range: 4.2498. Min Range: -4.2498

Max Act: 3.7242. Min Act: -0.0000

Data Index: 666471 (The Pile)

Max Activating Token Index: 896

Text #6

Max Range: 4.2498. Min Range: -4.2498

Max Act: 3.8658. Min Act: -0.0000

Data Index: 807347 (The Pile)

Max Activating Token Index: 37

Text #7

Max Range: 4.2498. Min Range: -4.2498

Max Act: 4.0318. Min Act: -0.0000

Data Index: 1576761 (The Pile)

Max Activating Token Index: 575

Text #8

Max Range: 4.2498. Min Range: -4.2498

Max Act: 3.7342. Min Act: -0.0000

Data Index: 1745377 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 4.2498. Min Range: -4.2498

Max Act: 3.8911. Min Act: -0.0000

Data Index: 1598752 (The Pile)

Max Activating Token Index: 406

Text #10

Max Range: 4.2498. Min Range: -4.2498

Max Act: 3.7032. Min Act: -0.0000

Data Index: 1424951 (The Pile)

Max Activating Token Index: 117

Text #11

Max Range: 4.2498. Min Range: -4.2498

Max Act: 3.5260. Min Act: -0.0000

Data Index: 191211 (The Pile)

Max Activating Token Index: 785

Text #12

Max Range: 4.2498. Min Range: -4.2498

Max Act: 3.5133. Min Act: -0.0000

Data Index: 18815 (The Pile)

Max Activating Token Index: 218

Text #13

Max Range: 4.2498. Min Range: -4.2498

Max Act: 3.8330. Min Act: -0.0000

Data Index: 236744 (The Pile)

Max Activating Token Index: 265

Text #14

Max Range: 4.2498. Min Range: -4.2498

Max Act: 3.8221. Min Act: -0.0000

Data Index: 138842 (The Pile)

Max Activating Token Index: 79

Text #15

Max Range: 4.2498. Min Range: -4.2498

Max Act: 3.8208. Min Act: -0.0000

Data Index: 331594 (The Pile)

Max Activating Token Index: 462

Text #16

Max Range: 4.2498. Min Range: -4.2498

Max Act: 3.2056. Min Act: -0.0000

Data Index: 925826 (The Pile)

Max Activating Token Index: 879

Text #17

Max Range: 4.2498. Min Range: -4.2498

Max Act: 3.8195. Min Act: -0.0000

Data Index: 207102 (The Pile)

Max Activating Token Index: 830

Text #18

Max Range: 4.2498. Min Range: -4.2498

Max Act: 3.6427. Min Act: -0.0000

Data Index: 592351 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 4.2498. Min Range: -4.2498

Max Act: 3.4559. Min Act: -0.0000

Data Index: 218440 (The Pile)

Max Activating Token Index: 484