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

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

Neuron 4687 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.9731. Min Act: -0.0002

Data Index: 284497 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.7152. Min Act: -0.0002

Data Index: 968833 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.7444. Min Act: -0.0002

Data Index: 365857 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.5030. Min Act: -0.0002

Data Index: 444374 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.5888. Min Act: -0.0002

Data Index: 998050 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.4750. Min Act: -0.0002

Data Index: 187480 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.5251. Min Act: -0.0002

Data Index: 678001 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.4015. Min Act: -0.0002

Data Index: 19568 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.2147. Min Act: -0.0002

Data Index: 995521 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.3024. Min Act: -0.0002

Data Index: 473573 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.0980. Min Act: -0.0002

Data Index: 161408 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.1048. Min Act: -0.0002

Data Index: 573532 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.1491. Min Act: -0.0002

Data Index: 449591 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.0101. Min Act: -0.0002

Data Index: 521792 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.0654. Min Act: -0.0002

Data Index: 1310745 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 5.9731. Min Range: -5.9731

Max Act: 4.9911. Min Act: -0.0002

Data Index: 1298595 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.0320. Min Act: -0.0002

Data Index: 724486 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.0556. Min Act: -0.0002

Data Index: 1331597 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 5.9731. Min Range: -5.9731

Max Act: 5.0332. Min Act: -0.0002

Data Index: 1091946 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 5.9731. Min Range: -5.9731

Max Act: 4.9920. Min Act: -0.0002

Data Index: 243255 (C4 (Web Text))

Max Activating Token Index: 287