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

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

Neuron 4092 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1828. Min Range: -1.1828

Max Act: 1.1622. Min Act: -0.0000

Data Index: 1336324 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 1.1828. Min Range: -1.1828

Max Act: 1.1442. Min Act: -0.0000

Data Index: 106238 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 1.1828. Min Range: -1.1828

Max Act: 1.0712. Min Act: -0.0000

Data Index: 950760 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 1.1828. Min Range: -1.1828

Max Act: 1.1828. Min Act: -0.0000

Data Index: 693427 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 1.1828. Min Range: -1.1828

Max Act: 1.0479. Min Act: -0.0000

Data Index: 1303409 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 1.1828. Min Range: -1.1828

Max Act: 1.0353. Min Act: -0.0000

Data Index: 696670 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 1.1828. Min Range: -1.1828

Max Act: 1.0065. Min Act: -0.0000

Data Index: 1044026 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.9645. Min Act: -0.0000

Data Index: 17245 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.9110. Min Act: -0.0000

Data Index: 712468 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.8813. Min Act: -0.0000

Data Index: 964172 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1259173 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.8577. Min Act: -0.0000

Data Index: 528481 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.8020. Min Act: -0.0000

Data Index: 766200 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.8227. Min Act: -0.0000

Data Index: 1017639 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.8463. Min Act: -0.0000

Data Index: 165659 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1046900 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.7628. Min Act: -0.0000

Data Index: 186058 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.7972. Min Act: -0.0000

Data Index: 707867 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.7184. Min Act: -0.0000

Data Index: 459793 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 1.1828. Min Range: -1.1828

Max Act: 0.7384. Min Act: -0.0000

Data Index: 737009 (C4 (Web Text))

Max Activating Token Index: 796