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

Dataset: The Pile

Neuron 2903 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: 0.2756. Min Range: -0.2756

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1159496 (The Pile)

Max Activating Token Index: 935

Text #1

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2721. Min Act: -0.0000

Data Index: 1465657 (The Pile)

Max Activating Token Index: 591

Text #2

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2597. Min Act: -0.0000

Data Index: 784973 (The Pile)

Max Activating Token Index: 497

Text #3

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1857510 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2488. Min Act: -0.0000

Data Index: 1226389 (The Pile)

Max Activating Token Index: 801

Text #5

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2421. Min Act: -0.0000

Data Index: 465377 (The Pile)

Max Activating Token Index: 296

Text #6

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1185300 (The Pile)

Max Activating Token Index: 640

Text #7

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2332. Min Act: -0.0000

Data Index: 1691025 (The Pile)

Max Activating Token Index: 586

Text #8

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2318. Min Act: -0.0000

Data Index: 973806 (The Pile)

Max Activating Token Index: 590

Text #9

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2476. Min Act: -0.0000

Data Index: 1469509 (The Pile)

Max Activating Token Index: 572

Text #10

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1732305 (The Pile)

Max Activating Token Index: 439

Text #11

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2398. Min Act: -0.0000

Data Index: 249944 (The Pile)

Max Activating Token Index: 843

Text #12

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2424. Min Act: -0.0000

Data Index: 105779 (The Pile)

Max Activating Token Index: 363

Text #13

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2472. Min Act: -0.0000

Data Index: 365308 (The Pile)

Max Activating Token Index: 154

Text #14

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2368. Min Act: -0.0000

Data Index: 648769 (The Pile)

Max Activating Token Index: 329

Text #15

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1559813 (The Pile)

Max Activating Token Index: 496

Text #16

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2237. Min Act: -0.0000

Data Index: 672366 (The Pile)

Max Activating Token Index: 356

Text #17

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1587552 (The Pile)

Max Activating Token Index: 720

Text #18

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2169. Min Act: -0.0000

Data Index: 104430 (The Pile)

Max Activating Token Index: 910

Text #19

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1986270 (The Pile)

Max Activating Token Index: 922