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

Dataset: The Pile

Neuron 210 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.4417. Min Range: -3.4417

Max Act: 3.4417. Min Act: -0.0000

Data Index: 1952938 (The Pile)

Max Activating Token Index: 531

Text #1

Max Range: 3.4417. Min Range: -3.4417

Max Act: 3.0958. Min Act: -0.0000

Data Index: 1047812 (The Pile)

Max Activating Token Index: 584

Text #2

Max Range: 3.4417. Min Range: -3.4417

Max Act: 3.2334. Min Act: -0.0000

Data Index: 1340299 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 3.4417. Min Range: -3.4417

Max Act: 3.0465. Min Act: -0.0000

Data Index: 920931 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 3.4417. Min Range: -3.4417

Max Act: 3.1264. Min Act: -0.0000

Data Index: 522993 (The Pile)

Max Activating Token Index: 523

Text #5

Max Range: 3.4417. Min Range: -3.4417

Max Act: 3.0131. Min Act: -0.0000

Data Index: 1462272 (The Pile)

Max Activating Token Index: 595

Text #6

Max Range: 3.4417. Min Range: -3.4417

Max Act: 3.1272. Min Act: -0.0000

Data Index: 812060 (The Pile)

Max Activating Token Index: 647

Text #7

Max Range: 3.4417. Min Range: -3.4417

Max Act: 2.8594. Min Act: -0.0000

Data Index: 1903669 (The Pile)

Max Activating Token Index: 813

Text #8

Max Range: 3.4417. Min Range: -3.4417

Max Act: 3.1222. Min Act: -0.0000

Data Index: 550874 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 3.4417. Min Range: -3.4417

Max Act: 2.9637. Min Act: -0.0000

Data Index: 154835 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 3.4417. Min Range: -3.4417

Max Act: 2.9539. Min Act: -0.0000

Data Index: 75932 (The Pile)

Max Activating Token Index: 572

Text #11

Max Range: 3.4417. Min Range: -3.4417

Max Act: 2.9438. Min Act: -0.0000

Data Index: 1994791 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 3.4417. Min Range: -3.4417

Max Act: 3.1861. Min Act: -0.0000

Data Index: 753102 (The Pile)

Max Activating Token Index: 548

Text #13

Max Range: 3.4417. Min Range: -3.4417

Max Act: 3.0451. Min Act: -0.0000

Data Index: 869962 (The Pile)

Max Activating Token Index: 545

Text #14

Max Range: 3.4417. Min Range: -3.4417

Max Act: 3.0476. Min Act: -0.0000

Data Index: 1988946 (The Pile)

Max Activating Token Index: 572

Text #15

Max Range: 3.4417. Min Range: -3.4417

Max Act: 3.0439. Min Act: -0.0000

Data Index: 390768 (The Pile)

Max Activating Token Index: 241

Text #16

Max Range: 3.4417. Min Range: -3.4417

Max Act: 3.0177. Min Act: -0.0000

Data Index: 332436 (The Pile)

Max Activating Token Index: 431

Text #17

Max Range: 3.4417. Min Range: -3.4417

Max Act: 3.0037. Min Act: -0.0000

Data Index: 1495946 (The Pile)

Max Activating Token Index: 446

Text #18

Max Range: 3.4417. Min Range: -3.4417

Max Act: 2.8839. Min Act: -0.0000

Data Index: 678041 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 3.4417. Min Range: -3.4417

Max Act: 2.7441. Min Act: -0.0000

Data Index: 757188 (The Pile)

Max Activating Token Index: 496