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

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

Neuron 2215 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5730. Min Range: -3.5730

Max Act: 3.5730. Min Act: -0.0001

Data Index: 821276 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.9048. Min Act: -0.0001

Data Index: 31773 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 3.5730. Min Range: -3.5730

Max Act: 3.4810. Min Act: -0.0001

Data Index: 589789 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 3.5730. Min Range: -3.5730

Max Act: 3.2478. Min Act: -0.0001

Data Index: 187999 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.3414. Min Act: -0.0001

Data Index: 41505 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.9929. Min Act: -0.0000

Data Index: 1182830 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.6862. Min Act: -0.0001

Data Index: 1026601 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.6470. Min Act: -0.0001

Data Index: 278414 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.2959. Min Act: -0.0001

Data Index: 882800 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.7084. Min Act: -0.0001

Data Index: 1093554 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.6216. Min Act: -0.0001

Data Index: 715317 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.2419. Min Act: -0.0001

Data Index: 247241 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.6014. Min Act: -0.0001

Data Index: 741697 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.4038. Min Act: -0.0001

Data Index: 933625 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.3759. Min Act: -0.0001

Data Index: 256978 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 3.5730. Min Range: -3.5730

Max Act: 1.8853. Min Act: -0.0001

Data Index: 1008308 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 3.5730. Min Range: -3.5730

Max Act: 1.3332. Min Act: -0.0001

Data Index: 46901 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 3.5730. Min Range: -3.5730

Max Act: 2.1532. Min Act: -0.0001

Data Index: 1116935 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 3.5730. Min Range: -3.5730

Max Act: 1.9186. Min Act: -0.0001

Data Index: 1351686 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 3.5730. Min Range: -3.5730

Max Act: 1.7124. Min Act: -0.0001

Data Index: 710284 (C4 (Web Text))

Max Activating Token Index: 812