Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4017 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0140. Min Range: -1.0140

Max Act: 1.0140. Min Act: -0.0000

Data Index: 83336 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.8907. Min Act: -0.0000

Data Index: 166847 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.9889. Min Act: -0.0000

Data Index: 1255826 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.8778. Min Act: -0.0000

Data Index: 434736 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.8235. Min Act: -0.0000

Data Index: 1320054 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1118116 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.8829. Min Act: -0.0000

Data Index: 978419 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1634384 (Python Code)

Max Activating Token Index: 343

Text #8

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.7107. Min Act: -0.0000

Data Index: 455857 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.7903. Min Act: -0.0000

Data Index: 706553 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1027259 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.8781. Min Act: -0.0000

Data Index: 1104409 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.8085. Min Act: -0.0000

Data Index: 1538487 (Python Code)

Max Activating Token Index: 128

Text #13

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.7260. Min Act: -0.0000

Data Index: 1318333 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6852. Min Act: -0.0000

Data Index: 1625093 (Python Code)

Max Activating Token Index: 984

Text #15

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.7250. Min Act: -0.0000

Data Index: 1541597 (Python Code)

Max Activating Token Index: 250

Text #16

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1552602 (Python Code)

Max Activating Token Index: 163

Text #17

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6715. Min Act: -0.0000

Data Index: 450466 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1465525 (Python Code)

Max Activating Token Index: 768

Text #19

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.7753. Min Act: -0.0000

Data Index: 438737 (C4 (Web Text))

Max Activating Token Index: 430