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

Dataset: The Pile

Neuron 4523 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: 0.6621. Min Range: -0.6621

Max Act: 0.6621. Min Act: -0.0000

Data Index: 1846622 (The Pile)

Max Activating Token Index: 711

Text #1

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.5246. Min Act: -0.0000

Data Index: 691946 (The Pile)

Max Activating Token Index: 411

Text #2

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.5716. Min Act: -0.0000

Data Index: 292411 (The Pile)

Max Activating Token Index: 529

Text #3

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1503707 (The Pile)

Max Activating Token Index: 559

Text #4

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4560. Min Act: -0.0000

Data Index: 886183 (The Pile)

Max Activating Token Index: 418

Text #5

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4562. Min Act: -0.0000

Data Index: 781714 (The Pile)

Max Activating Token Index: 233

Text #6

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4399. Min Act: -0.0000

Data Index: 324934 (The Pile)

Max Activating Token Index: 465

Text #7

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1777818 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4151. Min Act: -0.0000

Data Index: 475955 (The Pile)

Max Activating Token Index: 534

Text #9

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4423. Min Act: -0.0000

Data Index: 974338 (The Pile)

Max Activating Token Index: 471

Text #10

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4166. Min Act: -0.0000

Data Index: 866298 (The Pile)

Max Activating Token Index: 645

Text #11

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4206. Min Act: -0.0000

Data Index: 738643 (The Pile)

Max Activating Token Index: 886

Text #12

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4075. Min Act: -0.0000

Data Index: 731006 (The Pile)

Max Activating Token Index: 863

Text #13

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1533846 (The Pile)

Max Activating Token Index: 389

Text #14

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3993. Min Act: -0.0000

Data Index: 1474090 (The Pile)

Max Activating Token Index: 576

Text #15

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4048. Min Act: -0.0000

Data Index: 80572 (The Pile)

Max Activating Token Index: 459

Text #16

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3904. Min Act: -0.0000

Data Index: 620581 (The Pile)

Max Activating Token Index: 929

Text #17

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3993. Min Act: -0.0000

Data Index: 501333 (The Pile)

Max Activating Token Index: 317

Text #18

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1470995 (The Pile)

Max Activating Token Index: 399

Text #19

Max Range: 0.6621. Min Range: -0.6621

Max Act: 0.4401. Min Act: -0.0000

Data Index: 10491 (The Pile)

Max Activating Token Index: 764