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

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

Neuron 2111 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0069. Min Range: -7.0069

Max Act: 7.0069. Min Act: -0.0000

Data Index: 965829 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 7.0069. Min Range: -7.0069

Max Act: 6.9030. Min Act: -0.0000

Data Index: 203496 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 7.0069. Min Range: -7.0069

Max Act: 6.6279. Min Act: -0.0000

Data Index: 1350611 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 7.0069. Min Range: -7.0069

Max Act: 6.9032. Min Act: -0.0000

Data Index: 903634 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 7.0069. Min Range: -7.0069

Max Act: 6.3387. Min Act: -0.0000

Data Index: 469314 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 7.0069. Min Range: -7.0069

Max Act: 6.3784. Min Act: -0.0000

Data Index: 852337 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 7.0069. Min Range: -7.0069

Max Act: 6.3717. Min Act: -0.0000

Data Index: 1214176 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 7.0069. Min Range: -7.0069

Max Act: 5.9803. Min Act: -0.0000

Data Index: 1119062 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 7.0069. Min Range: -7.0069

Max Act: 5.8131. Min Act: -0.0000

Data Index: 580763 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 7.0069. Min Range: -7.0069

Max Act: 5.3036. Min Act: -0.0000

Data Index: 1241128 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 7.0069. Min Range: -7.0069

Max Act: 5.4081. Min Act: -0.0000

Data Index: 783378 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 7.0069. Min Range: -7.0069

Max Act: 5.2885. Min Act: -0.0000

Data Index: 161187 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 7.0069. Min Range: -7.0069

Max Act: 5.1804. Min Act: -0.0000

Data Index: 265627 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 7.0069. Min Range: -7.0069

Max Act: 5.3230. Min Act: -0.0000

Data Index: 660558 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 7.0069. Min Range: -7.0069

Max Act: 5.3452. Min Act: -0.0000

Data Index: 125166 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 7.0069. Min Range: -7.0069

Max Act: 5.3167. Min Act: -0.0000

Data Index: 1346583 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 7.0069. Min Range: -7.0069

Max Act: 5.0530. Min Act: -0.0000

Data Index: 154 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 7.0069. Min Range: -7.0069

Max Act: 4.8580. Min Act: -0.0000

Data Index: 318727 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 7.0069. Min Range: -7.0069

Max Act: 5.0419. Min Act: -0.0000

Data Index: 185280 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 7.0069. Min Range: -7.0069

Max Act: 4.7617. Min Act: -0.0000

Data Index: 1069366 (C4 (Web Text))

Max Activating Token Index: 72