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

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

Neuron 3502 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.5312. Min Act: -0.0000

Data Index: 287536 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.5789. Min Act: -0.0000

Data Index: 1039820 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.2633. Min Act: -0.0000

Data Index: 349461 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.3331. Min Act: -0.0000

Data Index: 1154005 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1825. Min Act: -0.0000

Data Index: 1259201 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.2434. Min Act: -0.0001

Data Index: 1342139 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1533. Min Act: -0.0001

Data Index: 391875 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.2541. Min Act: -0.0000

Data Index: 1005911 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.0845. Min Act: -0.0000

Data Index: 378346 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.0084. Min Act: -0.0001

Data Index: 261014 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.0761. Min Act: -0.0000

Data Index: 353958 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1500. Min Act: -0.0000

Data Index: 1164684 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1463. Min Act: -0.0000

Data Index: 73197 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.1801. Min Act: -0.0000

Data Index: 625298 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.0390. Min Act: -0.0000

Data Index: 708278 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.0397. Min Act: -0.0000

Data Index: 110863 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 1.5789. Min Range: -1.5789

Max Act: 0.8658. Min Act: -0.0000

Data Index: 1043830 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.0135. Min Act: -0.0001

Data Index: 1160625 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.0846. Min Act: -0.0000

Data Index: 270312 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 1.5789. Min Range: -1.5789

Max Act: 1.0996. Min Act: -0.0000

Data Index: 109785 (C4 (Web Text))

Max Activating Token Index: 836