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

Dataset: The Pile

Neuron 2844 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: 0.7287. Min Range: -0.7287

Max Act: 0.7173. Min Act: -0.0000

Data Index: 1209470 (The Pile)

Max Activating Token Index: 375

Text #1

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.7287. Min Act: -0.0000

Data Index: 664536 (The Pile)

Max Activating Token Index: 333

Text #2

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1564707 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6529. Min Act: -0.0000

Data Index: 1152207 (The Pile)

Max Activating Token Index: 898

Text #4

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1864123 (The Pile)

Max Activating Token Index: 390

Text #5

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1315428 (The Pile)

Max Activating Token Index: 481

Text #6

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6695. Min Act: -0.0001

Data Index: 1863615 (The Pile)

Max Activating Token Index: 579

Text #7

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1235651 (The Pile)

Max Activating Token Index: 842

Text #8

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6481. Min Act: -0.0000

Data Index: 620246 (The Pile)

Max Activating Token Index: 376

Text #9

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.7043. Min Act: -0.0000

Data Index: 283664 (The Pile)

Max Activating Token Index: 438

Text #10

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1463674 (The Pile)

Max Activating Token Index: 357

Text #11

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6699. Min Act: -0.0000

Data Index: 160324 (The Pile)

Max Activating Token Index: 420

Text #12

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6624. Min Act: -0.0000

Data Index: 207156 (The Pile)

Max Activating Token Index: 615

Text #13

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6538. Min Act: -0.0000

Data Index: 813123 (The Pile)

Max Activating Token Index: 235

Text #14

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6744. Min Act: -0.0000

Data Index: 1807457 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6951. Min Act: -0.0000

Data Index: 39249 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6413. Min Act: -0.0000

Data Index: 800956 (The Pile)

Max Activating Token Index: 548

Text #17

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.7075. Min Act: -0.0000

Data Index: 410841 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.7021. Min Act: -0.0000

Data Index: 1188492 (The Pile)

Max Activating Token Index: 21

Text #19

Max Range: 0.7287. Min Range: -0.7287

Max Act: 0.6754. Min Act: -0.0000

Data Index: 375470 (The Pile)

Max Activating Token Index: 523