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

Dataset: The Pile

Neuron 2713 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: 1.4177. Min Range: -1.4177

Max Act: 1.4177. Min Act: -0.0000

Data Index: 78103 (The Pile)

Max Activating Token Index: 522

Text #1

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.3359. Min Act: -0.0000

Data Index: 1073060 (The Pile)

Max Activating Token Index: 654

Text #2

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2564. Min Act: -0.0000

Data Index: 245556 (The Pile)

Max Activating Token Index: 438

Text #3

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2943. Min Act: -0.0000

Data Index: 509287 (The Pile)

Max Activating Token Index: 660

Text #4

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2529. Min Act: -0.0000

Data Index: 265134 (The Pile)

Max Activating Token Index: 750

Text #5

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2189. Min Act: -0.0000

Data Index: 165591 (The Pile)

Max Activating Token Index: 522

Text #6

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2426. Min Act: -0.0000

Data Index: 467145 (The Pile)

Max Activating Token Index: 514

Text #7

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2689. Min Act: -0.0000

Data Index: 1689988 (The Pile)

Max Activating Token Index: 965

Text #8

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2006. Min Act: -0.0000

Data Index: 576150 (The Pile)

Max Activating Token Index: 647

Text #9

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2251. Min Act: -0.0000

Data Index: 89025 (The Pile)

Max Activating Token Index: 597

Text #10

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2723. Min Act: -0.0000

Data Index: 351604 (The Pile)

Max Activating Token Index: 836

Text #11

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1955. Min Act: -0.0000

Data Index: 1272952 (The Pile)

Max Activating Token Index: 272

Text #12

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1612. Min Act: -0.0000

Data Index: 562509 (The Pile)

Max Activating Token Index: 1012

Text #13

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1390. Min Act: -0.0000

Data Index: 1417072 (The Pile)

Max Activating Token Index: 475

Text #14

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2338. Min Act: -0.0000

Data Index: 692819 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1999. Min Act: -0.0000

Data Index: 179407 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2517. Min Act: -0.0000

Data Index: 321707 (The Pile)

Max Activating Token Index: 756

Text #17

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1792. Min Act: -0.0000

Data Index: 1339224 (The Pile)

Max Activating Token Index: 482

Text #18

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1020. Min Act: -0.0000

Data Index: 38804 (The Pile)

Max Activating Token Index: 724

Text #19

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1934. Min Act: -0.0000

Data Index: 783908 (The Pile)

Max Activating Token Index: 674