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

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

Neuron 839 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.6634. Min Act: -0.0001

Data Index: 1296684 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.6173. Min Act: -0.0001

Data Index: 39299 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5466. Min Act: -0.0001

Data Index: 933693 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.5589. Min Act: -0.0001

Data Index: 1149150 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4762. Min Act: -0.0001

Data Index: 195774 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4740. Min Act: -0.0001

Data Index: 49818 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4787. Min Act: -0.0001

Data Index: 518542 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4583. Min Act: -0.0001

Data Index: 965579 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4629. Min Act: -0.0001

Data Index: 315831 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4554. Min Act: -0.0001

Data Index: 278036 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4260. Min Act: -0.0001

Data Index: 1154979 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4153. Min Act: -0.0001

Data Index: 89073 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4172. Min Act: -0.0001

Data Index: 894862 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.4221. Min Act: -0.0001

Data Index: 225765 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3876. Min Act: -0.0001

Data Index: 676135 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3941. Min Act: -0.0001

Data Index: 704526 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3979. Min Act: -0.0001

Data Index: 658644 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3897. Min Act: -0.0001

Data Index: 103307 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3999. Min Act: -0.0001

Data Index: 383797 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.6634. Min Range: -0.6634

Max Act: 0.3757. Min Act: -0.0001

Data Index: 330194 (C4 (Web Text))

Max Activating Token Index: 794