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

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

Neuron 5028 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7271. Min Range: -5.7271

Max Act: 5.7271. Min Act: -0.0001

Data Index: 576234 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 5.7271. Min Range: -5.7271

Max Act: 4.6843. Min Act: -0.0000

Data Index: 253664 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 5.7271. Min Range: -5.7271

Max Act: 5.0838. Min Act: -0.0000

Data Index: 541992 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 5.7271. Min Range: -5.7271

Max Act: 4.6900. Min Act: -0.0000

Data Index: 631371 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 5.7271. Min Range: -5.7271

Max Act: 4.4123. Min Act: -0.0000

Data Index: 545635 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 5.7271. Min Range: -5.7271

Max Act: 4.2763. Min Act: -0.0000

Data Index: 1318161 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 5.7271. Min Range: -5.7271

Max Act: 4.1569. Min Act: -0.0000

Data Index: 139689 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 5.7271. Min Range: -5.7271

Max Act: 3.5145. Min Act: -0.0000

Data Index: 1022601 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 5.7271. Min Range: -5.7271

Max Act: 4.0750. Min Act: -0.0000

Data Index: 649976 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 5.7271. Min Range: -5.7271

Max Act: 3.2579. Min Act: -0.0001

Data Index: 351460 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 5.7271. Min Range: -5.7271

Max Act: 3.6880. Min Act: -0.0000

Data Index: 1006024 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 5.7271. Min Range: -5.7271

Max Act: 3.6190. Min Act: -0.0000

Data Index: 535636 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 5.7271. Min Range: -5.7271

Max Act: 3.5642. Min Act: -0.0001

Data Index: 16390 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 5.7271. Min Range: -5.7271

Max Act: 3.7947. Min Act: -0.0001

Data Index: 389754 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 5.7271. Min Range: -5.7271

Max Act: 3.8385. Min Act: -0.0000

Data Index: 674462 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 5.7271. Min Range: -5.7271

Max Act: 3.6244. Min Act: -0.0000

Data Index: 839420 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 5.7271. Min Range: -5.7271

Max Act: 3.2469. Min Act: -0.0000

Data Index: 646070 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 5.7271. Min Range: -5.7271

Max Act: 3.1379. Min Act: -0.0001

Data Index: 1176590 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 5.7271. Min Range: -5.7271

Max Act: 3.6049. Min Act: -0.0001

Data Index: 694183 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 5.7271. Min Range: -5.7271

Max Act: 3.7746. Min Act: -0.0000

Data Index: 679459 (C4 (Web Text))

Max Activating Token Index: 481