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

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

Neuron 2191 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.9140. Min Act: -0.0000

Data Index: 1199455 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.4717. Min Act: -0.0000

Data Index: 984204 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.4089. Min Act: -0.0000

Data Index: 45582 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.4064. Min Act: -0.0000

Data Index: 918451 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.3501. Min Act: -0.0000

Data Index: 295487 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.4776. Min Act: -0.0000

Data Index: 111170 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.3011. Min Act: -0.0000

Data Index: 1331377 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.3012. Min Act: -0.0000

Data Index: 1232713 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.1527. Min Act: -0.0000

Data Index: 823890 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.1597. Min Act: -0.0000

Data Index: 730423 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.2091. Min Act: -0.0000

Data Index: 982472 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.2096. Min Act: -0.0000

Data Index: 603006 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.1960. Min Act: -0.0000

Data Index: 850452 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.1917. Min Act: -0.0000

Data Index: 97451 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.1734. Min Act: -0.0000

Data Index: 240237 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.2773. Min Act: -0.0000

Data Index: 544096 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.1363. Min Act: -0.0000

Data Index: 836114 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.1090. Min Act: -0.0000

Data Index: 642160 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 2.9140. Min Range: -2.9140

Max Act: 1.9727. Min Act: -0.0000

Data Index: 1242522 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 2.9140. Min Range: -2.9140

Max Act: 2.0607. Min Act: -0.0000

Data Index: 1324103 (C4 (Web Text))

Max Activating Token Index: 672