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

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

Neuron 4665 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.9059. Min Act: -0.0000

Data Index: 858099 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 4.1494. Min Range: -4.1494

Max Act: 4.1494. Min Act: -0.0000

Data Index: 328929 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.9617. Min Act: -0.0000

Data Index: 1157234 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.8079. Min Act: -0.0000

Data Index: 1114175 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.7528. Min Act: -0.0000

Data Index: 104841 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.5980. Min Act: -0.0000

Data Index: 1321562 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.7007. Min Act: -0.0000

Data Index: 1291198 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.3217. Min Act: -0.0000

Data Index: 291531 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.7803. Min Act: -0.0000

Data Index: 33624 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.5255. Min Act: -0.0000

Data Index: 483126 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.3649. Min Act: -0.0000

Data Index: 396935 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.7559. Min Act: -0.0000

Data Index: 1254605 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.4145. Min Act: -0.0000

Data Index: 981211 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 4.1494. Min Range: -4.1494

Max Act: 2.9573. Min Act: -0.0000

Data Index: 1093201 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.3694. Min Act: -0.0000

Data Index: 413584 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.5357. Min Act: -0.0001

Data Index: 361954 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.2061. Min Act: -0.0000

Data Index: 1029380 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.5132. Min Act: -0.0000

Data Index: 942838 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.1711. Min Act: -0.0000

Data Index: 930565 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 4.1494. Min Range: -4.1494

Max Act: 3.3006. Min Act: -0.0000

Data Index: 674871 (C4 (Web Text))

Max Activating Token Index: 9