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

Dataset: The Pile

Neuron 2165 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: 0.7473. Min Range: -0.7473

Max Act: 0.7227. Min Act: -0.0000

Data Index: 1964487 (The Pile)

Max Activating Token Index: 719

Text #1

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6096. Min Act: -0.0000

Data Index: 70361 (The Pile)

Max Activating Token Index: 304

Text #2

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6119. Min Act: -0.0000

Data Index: 1610280 (The Pile)

Max Activating Token Index: 113

Text #3

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1426596 (The Pile)

Max Activating Token Index: 419

Text #4

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1687633 (The Pile)

Max Activating Token Index: 366

Text #5

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.7473. Min Act: -0.0000

Data Index: 415106 (The Pile)

Max Activating Token Index: 737

Text #6

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1660425 (The Pile)

Max Activating Token Index: 20

Text #7

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.5112. Min Act: -0.0000

Data Index: 652115 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1579484 (The Pile)

Max Activating Token Index: 173

Text #9

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6031. Min Act: -0.0000

Data Index: 453264 (The Pile)

Max Activating Token Index: 774

Text #10

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.2686. Min Act: -0.0000

Data Index: 1171075 (The Pile)

Max Activating Token Index: 977

Text #11

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4781. Min Act: -0.0000

Data Index: 438080 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1096492 (The Pile)

Max Activating Token Index: 589

Text #13

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1555805 (The Pile)

Max Activating Token Index: 518

Text #14

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4762. Min Act: -0.0000

Data Index: 561410 (The Pile)

Max Activating Token Index: 257

Text #15

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.5263. Min Act: -0.0000

Data Index: 579244 (The Pile)

Max Activating Token Index: 293

Text #16

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4579. Min Act: -0.0000

Data Index: 1656031 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1470442 (The Pile)

Max Activating Token Index: 538

Text #18

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1989075 (The Pile)

Max Activating Token Index: 327

Text #19

Max Range: 0.7473. Min Range: -0.7473

Max Act: 0.4087. Min Act: -0.0000

Data Index: 448191 (The Pile)

Max Activating Token Index: 597