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

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

Neuron 4135 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: 4.3480. Min Range: -4.3480

Max Act: 4.3480. Min Act: -0.0000

Data Index: 945047 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.3452. Min Act: -0.0000

Data Index: 1242582 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.2746. Min Act: -0.0000

Data Index: 1134643 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.0854. Min Act: -0.0000

Data Index: 964755 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.2715. Min Act: -0.0000

Data Index: 1139128 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 4.3480. Min Range: -4.3480

Max Act: 3.0348. Min Act: -0.0000

Data Index: 112577 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 4.3480. Min Range: -4.3480

Max Act: 2.9728. Min Act: -0.0000

Data Index: 752726 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 4.3480. Min Range: -4.3480

Max Act: 2.9064. Min Act: -0.0000

Data Index: 497799 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 4.3480. Min Range: -4.3480

Max Act: 2.6945. Min Act: -0.0000

Data Index: 682316 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 4.3480. Min Range: -4.3480

Max Act: 2.6392. Min Act: -0.0000

Data Index: 1343200 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 4.3480. Min Range: -4.3480

Max Act: 2.7170. Min Act: -0.0000

Data Index: 1014795 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 4.3480. Min Range: -4.3480

Max Act: 2.7081. Min Act: -0.0000

Data Index: 400627 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 4.3480. Min Range: -4.3480

Max Act: 2.5276. Min Act: -0.0000

Data Index: 842027 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 4.3480. Min Range: -4.3480

Max Act: 2.2745. Min Act: -0.0000

Data Index: 756200 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 4.3480. Min Range: -4.3480

Max Act: 2.4075. Min Act: -0.0000

Data Index: 506185 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 4.3480. Min Range: -4.3480

Max Act: 2.3996. Min Act: -0.0000

Data Index: 772253 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 4.3480. Min Range: -4.3480

Max Act: 2.5036. Min Act: -0.0000

Data Index: 408358 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 4.3480. Min Range: -4.3480

Max Act: 2.2526. Min Act: -0.0000

Data Index: 619574 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 4.3480. Min Range: -4.3480

Max Act: 2.2251. Min Act: -0.0000

Data Index: 1239487 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 4.3480. Min Range: -4.3480

Max Act: 2.3339. Min Act: -0.0000

Data Index: 931859 (C4 (Web Text))

Max Activating Token Index: 445