Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3006 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.5914. Min Act: -0.0001

Data Index: 716299 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.5200. Min Act: -0.0001

Data Index: 395525 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.5068. Min Act: -0.0001

Data Index: 505145 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4563. Min Act: -0.0001

Data Index: 778182 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4533. Min Act: -0.0001

Data Index: 27267 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4304. Min Act: -0.0001

Data Index: 1150197 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4528. Min Act: -0.0001

Data Index: 113545 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4349. Min Act: -0.0001

Data Index: 107993 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4297. Min Act: -0.0000

Data Index: 674152 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4980. Min Act: 0.0000

Data Index: 423061 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4223. Min Act: -0.0001

Data Index: 1196512 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4230. Min Act: 0.0000

Data Index: 965728 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4237. Min Act: -0.0001

Data Index: 104311 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4185. Min Act: -0.0001

Data Index: 61579 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4048. Min Act: -0.0001

Data Index: 515131 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4149. Min Act: 0.0000

Data Index: 849397 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.3887. Min Act: 0.0000

Data Index: 1262798 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4015. Min Act: -0.0001

Data Index: 728241 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.3733. Min Act: -0.0001

Data Index: 532443 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 0.5914. Min Range: -0.5914

Max Act: 0.4271. Min Act: 0.0000

Data Index: 1118764 (C4 (Web Text))

Max Activating Token Index: 105