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

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

Neuron 1852 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6633. Min Range: -1.6633

Max Act: 1.6633. Min Act: -0.0000

Data Index: 937776 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.9805. Min Act: -0.0000

Data Index: 71879 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.8590. Min Act: -0.0000

Data Index: 610836 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.8081. Min Act: -0.0000

Data Index: 811213 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.8886. Min Act: -0.0001

Data Index: 42741 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.8140. Min Act: -0.0000

Data Index: 243487 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.8039. Min Act: -0.0000

Data Index: 292765 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.8357. Min Act: -0.0000

Data Index: 149322 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.8275. Min Act: -0.0000

Data Index: 660749 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.8121. Min Act: -0.0000

Data Index: 757136 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.8439. Min Act: -0.0000

Data Index: 1254446 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.7356. Min Act: -0.0000

Data Index: 179604 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.8427. Min Act: -0.0000

Data Index: 86392 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.7596. Min Act: -0.0000

Data Index: 345297 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.7791. Min Act: -0.0001

Data Index: 1355120 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.7468. Min Act: -0.0000

Data Index: 783347 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.7947. Min Act: -0.0000

Data Index: 550733 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.7462. Min Act: -0.0001

Data Index: 100303 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.7333. Min Act: -0.0000

Data Index: 1040039 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 1.6633. Min Range: -1.6633

Max Act: 0.7069. Min Act: -0.0000

Data Index: 268061 (C4 (Web Text))

Max Activating Token Index: 541