Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3383 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1504656 (The Pile)

Max Activating Token Index: 445

Text #1

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5669. Min Act: -0.0000

Data Index: 1789657 (The Pile)

Max Activating Token Index: 173

Text #2

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1987460 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1699765 (The Pile)

Max Activating Token Index: 506

Text #4

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1749966 (The Pile)

Max Activating Token Index: 589

Text #5

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1361527 (The Pile)

Max Activating Token Index: 541

Text #6

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1860797 (The Pile)

Max Activating Token Index: 125

Text #7

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1437224 (The Pile)

Max Activating Token Index: 278

Text #8

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5496. Min Act: -0.0000

Data Index: 428275 (The Pile)

Max Activating Token Index: 226

Text #9

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1462697 (The Pile)

Max Activating Token Index: 464

Text #10

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1122719 (The Pile)

Max Activating Token Index: 622

Text #11

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4526. Min Act: -0.0000

Data Index: 123089 (The Pile)

Max Activating Token Index: 715

Text #12

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4584. Min Act: -0.0000

Data Index: 1846500 (The Pile)

Max Activating Token Index: 294

Text #13

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1464823 (The Pile)

Max Activating Token Index: 418

Text #14

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.3828. Min Act: -0.0000

Data Index: 1491638 (The Pile)

Max Activating Token Index: 916

Text #15

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4707. Min Act: -0.0000

Data Index: 833180 (The Pile)

Max Activating Token Index: 513

Text #16

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1418700 (The Pile)

Max Activating Token Index: 618

Text #17

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4241. Min Act: -0.0000

Data Index: 876437 (The Pile)

Max Activating Token Index: 290

Text #18

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4256. Min Act: -0.0000

Data Index: 324122 (The Pile)

Max Activating Token Index: 907

Text #19

Max Range: 0.6494. Min Range: -0.6494

Max Act: 0.4327. Min Act: -0.0000

Data Index: 939561 (The Pile)

Max Activating Token Index: 274