Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2654 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0996. Min Act: -0.0002

Data Index: 981281 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0865. Min Act: -0.0001

Data Index: 231744 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1245644 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0988. Min Act: -0.0001

Data Index: 254958 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0939. Min Act: -0.0002

Data Index: 265251 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0918. Min Act: -0.0002

Data Index: 828421 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0965. Min Act: -0.0002

Data Index: 178881 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0844. Min Act: -0.0001

Data Index: 112803 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1222606 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0845. Min Act: -0.0001

Data Index: 1236827 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0843. Min Act: -0.0002

Data Index: 751355 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0896. Min Act: -0.0002

Data Index: 620503 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1248809 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0886. Min Act: -0.0002

Data Index: 688724 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0882. Min Act: -0.0002

Data Index: 1303030 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0848. Min Act: -0.0002

Data Index: 448153 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0846. Min Act: -0.0001

Data Index: 23032 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1193830 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0964. Min Act: -0.0002

Data Index: 416583 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1140398 (C4 (Web Text))

Max Activating Token Index: 853