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

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

Neuron 4359 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5730. Min Act: -0.0002

Data Index: 259474 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5405. Min Act: -0.0002

Data Index: 1168214 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5043. Min Act: -0.0002

Data Index: 3632 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5015. Min Act: -0.0002

Data Index: 792918 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.5078. Min Act: -0.0002

Data Index: 1058936 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4511. Min Act: -0.0002

Data Index: 75920 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4498. Min Act: -0.0002

Data Index: 689108 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4444. Min Act: -0.0002

Data Index: 810263 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4275. Min Act: -0.0002

Data Index: 1034971 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4411. Min Act: -0.0002

Data Index: 985346 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4481. Min Act: -0.0002

Data Index: 726499 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4494. Min Act: -0.0002

Data Index: 47431 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4428. Min Act: -0.0002

Data Index: 1210622 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4344. Min Act: -0.0002

Data Index: 799411 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4560. Min Act: -0.0002

Data Index: 189187 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4265. Min Act: -0.0002

Data Index: 43196 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4251. Min Act: -0.0002

Data Index: 907582 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4079. Min Act: -0.0002

Data Index: 927805 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4358. Min Act: -0.0002

Data Index: 1260436 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.5730. Min Range: -0.5730

Max Act: 0.4491. Min Act: -0.0002

Data Index: 59844 (C4 (Web Text))

Max Activating Token Index: 15