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

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

Neuron 5875 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.8529. Min Act: -0.0000

Data Index: 692211 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1148809 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.6856. Min Act: -0.0000

Data Index: 766904 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.6495. Min Act: -0.0000

Data Index: 158692 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.7132. Min Act: -0.0000

Data Index: 598308 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.7028. Min Act: -0.0000

Data Index: 948754 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1131169 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.6629. Min Act: -0.0000

Data Index: 959240 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1290830 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.6466. Min Act: -0.0000

Data Index: 114677 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.6448. Min Act: -0.0000

Data Index: 958164 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.6385. Min Act: -0.0000

Data Index: 240196 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.6397. Min Act: -0.0000

Data Index: 1021811 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.6562. Min Act: -0.0000

Data Index: 844025 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.5718. Min Act: -0.0000

Data Index: 841658 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.5970. Min Act: -0.0000

Data Index: 279096 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.6553. Min Act: -0.0000

Data Index: 654357 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.6837. Min Act: -0.0000

Data Index: 1007946 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.5875. Min Act: -0.0000

Data Index: 298017 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.8529. Min Range: -0.8529

Max Act: 0.6110. Min Act: -0.0000

Data Index: 1266146 (C4 (Web Text))

Max Activating Token Index: 711