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

Dataset: The Pile

Neuron 4037 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.5292. Min Act: -0.0000

Data Index: 59721 (The Pile)

Max Activating Token Index: 582

Text #1

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1409925 (The Pile)

Max Activating Token Index: 509

Text #2

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.5402. Min Act: -0.0000

Data Index: 687092 (The Pile)

Max Activating Token Index: 718

Text #3

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.5081. Min Act: -0.0000

Data Index: 847937 (The Pile)

Max Activating Token Index: 597

Text #4

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4916. Min Act: -0.0000

Data Index: 398607 (The Pile)

Max Activating Token Index: 355

Text #5

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.5373. Min Act: -0.0000

Data Index: 343961 (The Pile)

Max Activating Token Index: 293

Text #6

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4874. Min Act: -0.0000

Data Index: 98736 (The Pile)

Max Activating Token Index: 327

Text #7

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1931780 (The Pile)

Max Activating Token Index: 227

Text #8

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4740. Min Act: -0.0000

Data Index: 1889783 (The Pile)

Max Activating Token Index: 70

Text #9

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4693. Min Act: -0.0000

Data Index: 62540 (The Pile)

Max Activating Token Index: 224

Text #10

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4691. Min Act: -0.0000

Data Index: 888966 (The Pile)

Max Activating Token Index: 1009

Text #11

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4683. Min Act: -0.0000

Data Index: 801976 (The Pile)

Max Activating Token Index: 768

Text #12

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4945. Min Act: -0.0000

Data Index: 458882 (The Pile)

Max Activating Token Index: 245

Text #13

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4802. Min Act: -0.0000

Data Index: 81101 (The Pile)

Max Activating Token Index: 646

Text #14

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4432. Min Act: -0.0000

Data Index: 1825216 (The Pile)

Max Activating Token Index: 991

Text #15

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4609. Min Act: -0.0000

Data Index: 836378 (The Pile)

Max Activating Token Index: 306

Text #16

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4624. Min Act: -0.0000

Data Index: 163395 (The Pile)

Max Activating Token Index: 864

Text #17

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4726. Min Act: -0.0000

Data Index: 802202 (The Pile)

Max Activating Token Index: 853

Text #18

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4497. Min Act: -0.0000

Data Index: 178660 (The Pile)

Max Activating Token Index: 845

Text #19

Max Range: 0.5402. Min Range: -0.5402

Max Act: 0.4418. Min Act: -0.0000

Data Index: 613795 (The Pile)

Max Activating Token Index: 159