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

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

Neuron 4090 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3575. Min Range: -2.3575

Max Act: 2.3575. Min Act: -0.0000

Data Index: 1630207 (Python Code)

Max Activating Token Index: 61

Text #1

Max Range: 2.3575. Min Range: -2.3575

Max Act: 2.2109. Min Act: -0.0000

Data Index: 1566734 (Python Code)

Max Activating Token Index: 32

Text #2

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.7478. Min Act: -0.0000

Data Index: 1393536 (Python Code)

Max Activating Token Index: 912

Text #3

Max Range: 2.3575. Min Range: -2.3575

Max Act: 2.2391. Min Act: -0.0000

Data Index: 210129 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 2.3575. Min Range: -2.3575

Max Act: 2.1109. Min Act: -0.0000

Data Index: 1623599 (Python Code)

Max Activating Token Index: 622

Text #5

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.9698. Min Act: -0.0000

Data Index: 1525039 (Python Code)

Max Activating Token Index: 626

Text #6

Max Range: 2.3575. Min Range: -2.3575

Max Act: 2.0442. Min Act: -0.0000

Data Index: 1643986 (Python Code)

Max Activating Token Index: 844

Text #7

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.6296. Min Act: -0.0000

Data Index: 1459518 (Python Code)

Max Activating Token Index: 639

Text #8

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.8963. Min Act: -0.0000

Data Index: 1565425 (Python Code)

Max Activating Token Index: 509

Text #9

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.8250. Min Act: -0.0000

Data Index: 1477498 (Python Code)

Max Activating Token Index: 19

Text #10

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.8112. Min Act: -0.0000

Data Index: 1544213 (Python Code)

Max Activating Token Index: 72

Text #11

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.6124. Min Act: -0.0000

Data Index: 1588525 (Python Code)

Max Activating Token Index: 730

Text #12

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.8792. Min Act: -0.0000

Data Index: 1591568 (Python Code)

Max Activating Token Index: 62

Text #13

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.6876. Min Act: -0.0000

Data Index: 1436324 (Python Code)

Max Activating Token Index: 713

Text #14

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.5597. Min Act: -0.0000

Data Index: 1636916 (Python Code)

Max Activating Token Index: 838

Text #15

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.6860. Min Act: -0.0000

Data Index: 1556948 (Python Code)

Max Activating Token Index: 22

Text #16

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.6709. Min Act: -0.0000

Data Index: 623463 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.7559. Min Act: -0.0000

Data Index: 1408716 (Python Code)

Max Activating Token Index: 708

Text #18

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.7611. Min Act: -0.0000

Data Index: 1602572 (Python Code)

Max Activating Token Index: 893

Text #19

Max Range: 2.3575. Min Range: -2.3575

Max Act: 1.4931. Min Act: -0.0000

Data Index: 1384947 (Python Code)

Max Activating Token Index: 1003