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

Dataset: The Pile

Neuron 4705 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.5203. Min Act: -0.0000

Data Index: 691769 (The Pile)

Max Activating Token Index: 414

Text #1

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.4938. Min Act: -0.0000

Data Index: 368110 (The Pile)

Max Activating Token Index: 667

Text #2

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.3246. Min Act: -0.0000

Data Index: 1609655 (The Pile)

Max Activating Token Index: 877

Text #3

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.4801. Min Act: -0.0000

Data Index: 1920079 (The Pile)

Max Activating Token Index: 961

Text #4

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.4026. Min Act: -0.0000

Data Index: 1259265 (The Pile)

Max Activating Token Index: 571

Text #5

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.4030. Min Act: -0.0000

Data Index: 1765759 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.2875. Min Act: -0.0000

Data Index: 1598752 (The Pile)

Max Activating Token Index: 248

Text #7

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.2674. Min Act: -0.0000

Data Index: 1961273 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.3228. Min Act: -0.0000

Data Index: 107810 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.3327. Min Act: -0.0000

Data Index: 1906077 (The Pile)

Max Activating Token Index: 892

Text #10

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.3338. Min Act: -0.0000

Data Index: 1443129 (The Pile)

Max Activating Token Index: 1020

Text #11

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.2704. Min Act: -0.0000

Data Index: 254162 (The Pile)

Max Activating Token Index: 217

Text #12

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.2774. Min Act: -0.0000

Data Index: 1583126 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.2372. Min Act: -0.0000

Data Index: 1532415 (The Pile)

Max Activating Token Index: 728

Text #14

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.2696. Min Act: -0.0000

Data Index: 1516671 (The Pile)

Max Activating Token Index: 363

Text #15

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.2521. Min Act: -0.0000

Data Index: 1875667 (The Pile)

Max Activating Token Index: 389

Text #16

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.2557. Min Act: -0.0000

Data Index: 581658 (The Pile)

Max Activating Token Index: 324

Text #17

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.2470. Min Act: -0.0000

Data Index: 503507 (The Pile)

Max Activating Token Index: 262

Text #18

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.3196. Min Act: -0.0000

Data Index: 635459 (The Pile)

Max Activating Token Index: 381

Text #19

Max Range: 1.5203. Min Range: -1.5203

Max Act: 1.1737. Min Act: -0.0000

Data Index: 1088519 (The Pile)

Max Activating Token Index: 278