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

Dataset: The Pile

Neuron 1176 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.3520. Min Act: -0.0000

Data Index: 1995204 (The Pile)

Max Activating Token Index: 82

Text #1

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2981. Min Act: -0.0000

Data Index: 305164 (The Pile)

Max Activating Token Index: 857

Text #2

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1679364 (The Pile)

Max Activating Token Index: 46

Text #3

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2768. Min Act: -0.0000

Data Index: 91585 (The Pile)

Max Activating Token Index: 52

Text #4

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1980757 (The Pile)

Max Activating Token Index: 287

Text #5

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1074550 (The Pile)

Max Activating Token Index: 775

Text #6

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2645. Min Act: -0.0000

Data Index: 32059 (The Pile)

Max Activating Token Index: 622

Text #7

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2526. Min Act: -0.0000

Data Index: 556641 (The Pile)

Max Activating Token Index: 718

Text #8

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2506. Min Act: -0.0000

Data Index: 640822 (The Pile)

Max Activating Token Index: 242

Text #9

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2480. Min Act: -0.0000

Data Index: 866077 (The Pile)

Max Activating Token Index: 370

Text #10

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2133. Min Act: -0.0000

Data Index: 1508931 (The Pile)

Max Activating Token Index: 737

Text #11

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2608. Min Act: -0.0000

Data Index: 554554 (The Pile)

Max Activating Token Index: 367

Text #12

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1492442 (The Pile)

Max Activating Token Index: 374

Text #13

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2488. Min Act: -0.0000

Data Index: 784563 (The Pile)

Max Activating Token Index: 123

Text #14

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2238. Min Act: -0.0000

Data Index: 702556 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1806889 (The Pile)

Max Activating Token Index: 938

Text #16

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2441. Min Act: -0.0000

Data Index: 302691 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2439. Min Act: -0.0000

Data Index: 208513 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1268815 (The Pile)

Max Activating Token Index: 494

Text #19

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2167. Min Act: -0.0000

Data Index: 1456503 (The Pile)

Max Activating Token Index: 651