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

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

Neuron 4746 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.4606. Min Act: -0.0000

Data Index: 1632744 (Python Code)

Max Activating Token Index: 830

Text #1

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.9116. Min Act: -0.0000

Data Index: 1566635 (Python Code)

Max Activating Token Index: 742

Text #2

Max Range: 3.4606. Min Range: -3.4606

Max Act: 3.1125. Min Act: -0.0000

Data Index: 1635456 (Python Code)

Max Activating Token Index: 194

Text #3

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.9846. Min Act: -0.0000

Data Index: 857557 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.7790. Min Act: -0.0000

Data Index: 1561072 (Python Code)

Max Activating Token Index: 317

Text #5

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.7786. Min Act: -0.0000

Data Index: 482765 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.7066. Min Act: -0.0000

Data Index: 527172 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.7960. Min Act: -0.0000

Data Index: 370089 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.6561. Min Act: -0.0000

Data Index: 1589602 (Python Code)

Max Activating Token Index: 138

Text #9

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.6413. Min Act: -0.0000

Data Index: 43767 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.5853. Min Act: -0.0000

Data Index: 1637672 (Python Code)

Max Activating Token Index: 530

Text #11

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.6092. Min Act: -0.0000

Data Index: 813236 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.6995. Min Act: -0.0000

Data Index: 296933 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.7002. Min Act: -0.0000

Data Index: 1406169 (Python Code)

Max Activating Token Index: 534

Text #14

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.6734. Min Act: -0.0000

Data Index: 1210905 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.6792. Min Act: -0.0000

Data Index: 168669 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.6538. Min Act: -0.0000

Data Index: 738979 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.5995. Min Act: -0.0000

Data Index: 1063854 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.5163. Min Act: -0.0000

Data Index: 1596274 (Python Code)

Max Activating Token Index: 250

Text #19

Max Range: 3.4606. Min Range: -3.4606

Max Act: 2.6738. Min Act: -0.0000

Data Index: 100002 (C4 (Web Text))

Max Activating Token Index: 361