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

Dataset: The Pile

Neuron 505 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: 1.8733. Min Range: -1.8733

Max Act: 1.8733. Min Act: -0.0000

Data Index: 903665 (The Pile)

Max Activating Token Index: 434

Text #1

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.6290. Min Act: -0.0000

Data Index: 945188 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.5517. Min Act: -0.0000

Data Index: 87524 (The Pile)

Max Activating Token Index: 399

Text #3

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.4402. Min Act: -0.0000

Data Index: 116003 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.4797. Min Act: -0.0000

Data Index: 1554501 (The Pile)

Max Activating Token Index: 16

Text #5

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.2968. Min Act: -0.0000

Data Index: 110388 (The Pile)

Max Activating Token Index: 75

Text #6

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.5346. Min Act: -0.0000

Data Index: 401636 (The Pile)

Max Activating Token Index: 331

Text #7

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.3680. Min Act: -0.0000

Data Index: 906971 (The Pile)

Max Activating Token Index: 153

Text #8

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.3251. Min Act: -0.0000

Data Index: 1626690 (The Pile)

Max Activating Token Index: 350

Text #9

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.4674. Min Act: -0.0000

Data Index: 1443157 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.3367. Min Act: -0.0000

Data Index: 1142180 (The Pile)

Max Activating Token Index: 76

Text #11

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.4390. Min Act: -0.0000

Data Index: 1299488 (The Pile)

Max Activating Token Index: 601

Text #12

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.2543. Min Act: -0.0000

Data Index: 173883 (The Pile)

Max Activating Token Index: 107

Text #13

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.2010. Min Act: -0.0000

Data Index: 715675 (The Pile)

Max Activating Token Index: 742

Text #14

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.3010. Min Act: -0.0000

Data Index: 1101751 (The Pile)

Max Activating Token Index: 772

Text #15

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.2256. Min Act: -0.0000

Data Index: 269289 (The Pile)

Max Activating Token Index: 438

Text #16

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.2615. Min Act: -0.0000

Data Index: 771094 (The Pile)

Max Activating Token Index: 464

Text #17

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.2558. Min Act: -0.0000

Data Index: 686781 (The Pile)

Max Activating Token Index: 87

Text #18

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.2970. Min Act: -0.0000

Data Index: 1218355 (The Pile)

Max Activating Token Index: 705

Text #19

Max Range: 1.8733. Min Range: -1.8733

Max Act: 1.2770. Min Act: -0.0000

Data Index: 1069087 (The Pile)

Max Activating Token Index: 1014