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

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

Neuron 2682 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8562. Min Range: -5.8562

Max Act: 5.8562. Min Act: -0.0000

Data Index: 311918 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 5.8562. Min Range: -5.8562

Max Act: 5.7068. Min Act: -0.0000

Data Index: 566124 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 5.8562. Min Range: -5.8562

Max Act: 4.8143. Min Act: -0.0000

Data Index: 796730 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 5.8562. Min Range: -5.8562

Max Act: 4.9044. Min Act: -0.0000

Data Index: 376731 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 5.8562. Min Range: -5.8562

Max Act: 5.3640. Min Act: -0.0000

Data Index: 144312 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 5.8562. Min Range: -5.8562

Max Act: 5.0908. Min Act: -0.0000

Data Index: 813104 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 5.8562. Min Range: -5.8562

Max Act: 4.9294. Min Act: -0.0000

Data Index: 1103943 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 5.8562. Min Range: -5.8562

Max Act: 4.8005. Min Act: -0.0000

Data Index: 393763 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 5.8562. Min Range: -5.8562

Max Act: 4.8602. Min Act: -0.0000

Data Index: 758622 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 5.8562. Min Range: -5.8562

Max Act: 4.2467. Min Act: -0.0000

Data Index: 214394 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 5.8562. Min Range: -5.8562

Max Act: 4.3978. Min Act: -0.0000

Data Index: 1333910 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 5.8562. Min Range: -5.8562

Max Act: 4.7662. Min Act: -0.0000

Data Index: 562076 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 5.8562. Min Range: -5.8562

Max Act: 4.0315. Min Act: -0.0000

Data Index: 9804 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 5.8562. Min Range: -5.8562

Max Act: 4.4826. Min Act: -0.0000

Data Index: 62201 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 5.8562. Min Range: -5.8562

Max Act: 4.5214. Min Act: -0.0000

Data Index: 1214546 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 5.8562. Min Range: -5.8562

Max Act: 4.6672. Min Act: -0.0000

Data Index: 1295242 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 5.8562. Min Range: -5.8562

Max Act: 4.1644. Min Act: -0.0000

Data Index: 1118437 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 5.8562. Min Range: -5.8562

Max Act: 4.4143. Min Act: -0.0000

Data Index: 1300476 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 5.8562. Min Range: -5.8562

Max Act: 4.6091. Min Act: -0.0000

Data Index: 26701 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 5.8562. Min Range: -5.8562

Max Act: 4.5851. Min Act: -0.0000

Data Index: 876640 (C4 (Web Text))

Max Activating Token Index: 668