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

Dataset: The Pile

Neuron 2695 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: 0.3316. Min Range: -0.3316

Max Act: 0.3316. Min Act: -0.0000

Data Index: 38233 (The Pile)

Max Activating Token Index: 570

Text #1

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.3094. Min Act: -0.0000

Data Index: 177652 (The Pile)

Max Activating Token Index: 597

Text #2

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2835. Min Act: -0.0000

Data Index: 441013 (The Pile)

Max Activating Token Index: 184

Text #3

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2759. Min Act: -0.0000

Data Index: 1518094 (The Pile)

Max Activating Token Index: 903

Text #4

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2982. Min Act: -0.0000

Data Index: 875646 (The Pile)

Max Activating Token Index: 635

Text #5

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1238131 (The Pile)

Max Activating Token Index: 669

Text #6

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1747708 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1259242 (The Pile)

Max Activating Token Index: 303

Text #8

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2639. Min Act: -0.0000

Data Index: 969292 (The Pile)

Max Activating Token Index: 187

Text #9

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2721. Min Act: -0.0000

Data Index: 215689 (The Pile)

Max Activating Token Index: 320

Text #10

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1778701 (The Pile)

Max Activating Token Index: 364

Text #11

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1819344 (The Pile)

Max Activating Token Index: 645

Text #12

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1865385 (The Pile)

Max Activating Token Index: 532

Text #13

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1442161 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2453. Min Act: -0.0000

Data Index: 164632 (The Pile)

Max Activating Token Index: 822

Text #15

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2536. Min Act: -0.0000

Data Index: 781251 (The Pile)

Max Activating Token Index: 175

Text #16

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1151666 (The Pile)

Max Activating Token Index: 290

Text #17

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1522329 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1510913 (The Pile)

Max Activating Token Index: 645

Text #19

Max Range: 0.3316. Min Range: -0.3316

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1484929 (The Pile)

Max Activating Token Index: 915