Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2933 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0673. Min Act: -0.0003

Data Index: 1354205 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1439544 (Python Code)

Max Activating Token Index: 158

Text #2

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0608. Min Act: -0.0003

Data Index: 1576561 (Python Code)

Max Activating Token Index: 466

Text #3

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1523875 (Python Code)

Max Activating Token Index: 567

Text #4

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0512. Min Act: -0.0003

Data Index: 1621835 (Python Code)

Max Activating Token Index: 761

Text #5

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0552. Min Act: -0.0003

Data Index: 1567793 (Python Code)

Max Activating Token Index: 525

Text #6

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0553. Min Act: -0.0003

Data Index: 813693 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0590. Min Act: -0.0003

Data Index: 995491 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0574. Min Act: -0.0003

Data Index: 1261135 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0546. Min Act: -0.0003

Data Index: 1617247 (Python Code)

Max Activating Token Index: 634

Text #10

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0560. Min Act: -0.0003

Data Index: 732737 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0498. Min Act: -0.0003

Data Index: 1365827 (Python Code)

Max Activating Token Index: 188

Text #12

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0587. Min Act: -0.0003

Data Index: 1510365 (Python Code)

Max Activating Token Index: 152

Text #13

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0532. Min Act: -0.0003

Data Index: 348019 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0542. Min Act: -0.0003

Data Index: 1452093 (Python Code)

Max Activating Token Index: 71

Text #15

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1436260 (Python Code)

Max Activating Token Index: 997

Text #16

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0614. Min Act: -0.0003

Data Index: 1601198 (Python Code)

Max Activating Token Index: 271

Text #17

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0571. Min Act: -0.0003

Data Index: 1448387 (Python Code)

Max Activating Token Index: 338

Text #18

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0542. Min Act: -0.0003

Data Index: 1520688 (Python Code)

Max Activating Token Index: 214

Text #19

Max Range: 0.0673. Min Range: -0.0673

Max Act: 0.0557. Min Act: -0.0003

Data Index: 568182 (C4 (Web Text))

Max Activating Token Index: 548