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

Dataset: The Pile

Neuron 5037 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6663. Min Range: -3.6663

Max Act: 2.8252. Min Act: -0.0000

Data Index: 972289 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.6447. Min Act: -0.0000

Data Index: 714736 (The Pile)

Max Activating Token Index: 483

Text #2

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.6663. Min Act: -0.0000

Data Index: 1929972 (The Pile)

Max Activating Token Index: 738

Text #3

Max Range: 3.6663. Min Range: -3.6663

Max Act: 2.9174. Min Act: -0.0000

Data Index: 1389404 (The Pile)

Max Activating Token Index: 926

Text #4

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.4347. Min Act: -0.0000

Data Index: 98895 (The Pile)

Max Activating Token Index: 911

Text #5

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.2466. Min Act: -0.0000

Data Index: 1088716 (The Pile)

Max Activating Token Index: 754

Text #6

Max Range: 3.6663. Min Range: -3.6663

Max Act: 2.3251. Min Act: -0.0000

Data Index: 1928247 (The Pile)

Max Activating Token Index: 874

Text #7

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.0825. Min Act: -0.0000

Data Index: 1171026 (The Pile)

Max Activating Token Index: 336

Text #8

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.3790. Min Act: -0.0000

Data Index: 1342935 (The Pile)

Max Activating Token Index: 419

Text #9

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.1771. Min Act: -0.0000

Data Index: 1224020 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 3.6663. Min Range: -3.6663

Max Act: 2.7159. Min Act: -0.0000

Data Index: 1066996 (The Pile)

Max Activating Token Index: 665

Text #11

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.2392. Min Act: -0.0000

Data Index: 822628 (The Pile)

Max Activating Token Index: 274

Text #12

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.0982. Min Act: -0.0000

Data Index: 1519927 (The Pile)

Max Activating Token Index: 374

Text #13

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.1674. Min Act: -0.0000

Data Index: 1024801 (The Pile)

Max Activating Token Index: 415

Text #14

Max Range: 3.6663. Min Range: -3.6663

Max Act: 2.7546. Min Act: -0.0000

Data Index: 631037 (The Pile)

Max Activating Token Index: 438

Text #15

Max Range: 3.6663. Min Range: -3.6663

Max Act: 2.9790. Min Act: -0.0000

Data Index: 393355 (The Pile)

Max Activating Token Index: 884

Text #16

Max Range: 3.6663. Min Range: -3.6663

Max Act: 2.9333. Min Act: -0.0001

Data Index: 1249434 (The Pile)

Max Activating Token Index: 694

Text #17

Max Range: 3.6663. Min Range: -3.6663

Max Act: 2.9506. Min Act: -0.0000

Data Index: 455175 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 3.6663. Min Range: -3.6663

Max Act: 3.0923. Min Act: -0.0000

Data Index: 231323 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 3.6663. Min Range: -3.6663

Max Act: 2.9306. Min Act: -0.0000

Data Index: 674670 (The Pile)

Max Activating Token Index: 432