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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3892 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7753. Min Range: -5.7753

Max Act: 5.7753. Min Act: -0.0000

Data Index: 1003596 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 5.7753. Min Range: -5.7753

Max Act: 4.2831. Min Act: -0.0000

Data Index: 825018 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 5.7753. Min Range: -5.7753

Max Act: 4.2952. Min Act: -0.0000

Data Index: 1246413 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 5.7753. Min Range: -5.7753

Max Act: 3.5692. Min Act: -0.0000

Data Index: 319765 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 5.7753. Min Range: -5.7753

Max Act: 3.6336. Min Act: -0.0000

Data Index: 375919 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 5.7753. Min Range: -5.7753

Max Act: 4.0120. Min Act: -0.0000

Data Index: 1347618 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 5.7753. Min Range: -5.7753

Max Act: 3.5529. Min Act: -0.0000

Data Index: 455243 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 5.7753. Min Range: -5.7753

Max Act: 3.6440. Min Act: -0.0000

Data Index: 183117 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 5.7753. Min Range: -5.7753

Max Act: 2.8538. Min Act: -0.0001

Data Index: 1325446 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 5.7753. Min Range: -5.7753

Max Act: 3.2337. Min Act: -0.0000

Data Index: 833403 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 5.7753. Min Range: -5.7753

Max Act: 3.1948. Min Act: -0.0000

Data Index: 752702 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 5.7753. Min Range: -5.7753

Max Act: 3.6344. Min Act: -0.0000

Data Index: 369634 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 5.7753. Min Range: -5.7753

Max Act: 3.3114. Min Act: -0.0000

Data Index: 1239584 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 5.7753. Min Range: -5.7753

Max Act: 3.3051. Min Act: -0.0000

Data Index: 548431 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 5.7753. Min Range: -5.7753

Max Act: 3.7880. Min Act: -0.0000

Data Index: 351628 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 5.7753. Min Range: -5.7753

Max Act: 3.1392. Min Act: -0.0000

Data Index: 818240 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 5.7753. Min Range: -5.7753

Max Act: 3.4505. Min Act: -0.0000

Data Index: 1107286 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 5.7753. Min Range: -5.7753

Max Act: 3.6114. Min Act: -0.0000

Data Index: 791169 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 5.7753. Min Range: -5.7753

Max Act: 3.2790. Min Act: -0.0000

Data Index: 565750 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 5.7753. Min Range: -5.7753

Max Act: 3.1297. Min Act: -0.0000

Data Index: 129098 (C4 (Web Text))

Max Activating Token Index: 415