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

Dataset: The Pile

Neuron 3629 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: 0.4561. Min Range: -0.4561

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1730111 (The Pile)

Max Activating Token Index: 359

Text #1

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3370. Min Act: -0.0000

Data Index: 499369 (The Pile)

Max Activating Token Index: 796

Text #2

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1978423 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2987. Min Act: -0.0000

Data Index: 872371 (The Pile)

Max Activating Token Index: 223

Text #4

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3026. Min Act: -0.0000

Data Index: 1772819 (The Pile)

Max Activating Token Index: 204

Text #5

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.3262. Min Act: -0.0000

Data Index: 38187 (The Pile)

Max Activating Token Index: 822

Text #6

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2426. Min Act: -0.0000

Data Index: 304751 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2335. Min Act: -0.0000

Data Index: 357344 (The Pile)

Max Activating Token Index: 900

Text #8

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2681. Min Act: -0.0000

Data Index: 881263 (The Pile)

Max Activating Token Index: 568

Text #9

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1666434 (The Pile)

Max Activating Token Index: 212

Text #10

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2582. Min Act: -0.0000

Data Index: 269922 (The Pile)

Max Activating Token Index: 96

Text #11

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2478. Min Act: -0.0000

Data Index: 579972 (The Pile)

Max Activating Token Index: 890

Text #12

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1602048 (The Pile)

Max Activating Token Index: 538

Text #13

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2068. Min Act: -0.0000

Data Index: 426802 (The Pile)

Max Activating Token Index: 990

Text #14

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1691430 (The Pile)

Max Activating Token Index: 558

Text #15

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1458947 (The Pile)

Max Activating Token Index: 959

Text #16

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2399. Min Act: -0.0000

Data Index: 883646 (The Pile)

Max Activating Token Index: 736

Text #17

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2292. Min Act: -0.0000

Data Index: 530099 (The Pile)

Max Activating Token Index: 808

Text #18

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2605. Min Act: -0.0000

Data Index: 1286411 (The Pile)

Max Activating Token Index: 166

Text #19

Max Range: 0.4561. Min Range: -0.4561

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1611556 (The Pile)

Max Activating Token Index: 275