Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5551 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.7919. Min Range: -3.7919

Max Act: 3.7642. Min Act: -0.0000

Data Index: 477281 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 3.7919. Min Range: -3.7919

Max Act: 3.6737. Min Act: -0.0000

Data Index: 1104697 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 3.7919. Min Range: -3.7919

Max Act: 3.5706. Min Act: -0.0000

Data Index: 54266 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 3.7919. Min Range: -3.7919

Max Act: 3.3809. Min Act: -0.0000

Data Index: 117868 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 3.7919. Min Range: -3.7919

Max Act: 3.7919. Min Act: -0.0000

Data Index: 724499 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 3.7919. Min Range: -3.7919

Max Act: 3.1783. Min Act: -0.0000

Data Index: 382059 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 3.7919. Min Range: -3.7919

Max Act: 3.4357. Min Act: -0.0000

Data Index: 753327 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 3.7919. Min Range: -3.7919

Max Act: 3.0809. Min Act: -0.0000

Data Index: 1022530 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 3.7919. Min Range: -3.7919

Max Act: 2.8562. Min Act: -0.0000

Data Index: 496599 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 3.7919. Min Range: -3.7919

Max Act: 3.0150. Min Act: -0.0000

Data Index: 967106 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 3.7919. Min Range: -3.7919

Max Act: 3.0304. Min Act: -0.0000

Data Index: 798390 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 3.7919. Min Range: -3.7919

Max Act: 2.8702. Min Act: -0.0000

Data Index: 436762 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 3.7919. Min Range: -3.7919

Max Act: 3.1057. Min Act: -0.0000

Data Index: 1271762 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 3.7919. Min Range: -3.7919

Max Act: 2.9424. Min Act: -0.0000

Data Index: 1251817 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 3.7919. Min Range: -3.7919

Max Act: 2.9261. Min Act: -0.0000

Data Index: 973409 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 3.7919. Min Range: -3.7919

Max Act: 3.2331. Min Act: -0.0000

Data Index: 729135 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 3.7919. Min Range: -3.7919

Max Act: 2.7277. Min Act: -0.0000

Data Index: 1168240 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 3.7919. Min Range: -3.7919

Max Act: 2.8524. Min Act: -0.0000

Data Index: 355130 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 3.7919. Min Range: -3.7919

Max Act: 3.0116. Min Act: -0.0000

Data Index: 93473 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 3.7919. Min Range: -3.7919

Max Act: 2.6608. Min Act: -0.0000

Data Index: 1284042 (C4 (Web Text))

Max Activating Token Index: 614