Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4852 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1428962 (Python Code)

Max Activating Token Index: 523

Text #1

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1518841 (Python Code)

Max Activating Token Index: 143

Text #2

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0672. Min Act: -0.0001

Data Index: 239485 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1637527 (Python Code)

Max Activating Token Index: 951

Text #4

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1405795 (Python Code)

Max Activating Token Index: 156

Text #5

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0622. Min Act: -0.0001

Data Index: 1568968 (Python Code)

Max Activating Token Index: 856

Text #6

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0617. Min Act: -0.0000

Data Index: 737104 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0601. Min Act: -0.0000

Data Index: 1480095 (Python Code)

Max Activating Token Index: 819

Text #8

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0585. Min Act: -0.0001

Data Index: 1610273 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0564. Min Act: -0.0000

Data Index: 1497311 (Python Code)

Max Activating Token Index: 961

Text #10

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0546. Min Act: -0.0000

Data Index: 1388946 (Python Code)

Max Activating Token Index: 43

Text #11

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0561. Min Act: -0.0000

Data Index: 1428493 (Python Code)

Max Activating Token Index: 104

Text #12

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0558. Min Act: -0.0000

Data Index: 1393549 (Python Code)

Max Activating Token Index: 150

Text #13

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0520. Min Act: -0.0000

Data Index: 1583039 (Python Code)

Max Activating Token Index: 148

Text #14

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1641419 (Python Code)

Max Activating Token Index: 294

Text #15

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1620199 (Python Code)

Max Activating Token Index: 187

Text #16

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1040713 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0522. Min Act: -0.0000

Data Index: 1569267 (Python Code)

Max Activating Token Index: 883

Text #18

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1655584 (Python Code)

Max Activating Token Index: 311

Text #19

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0534. Min Act: -0.0000

Data Index: 230024 (C4 (Web Text))

Max Activating Token Index: 814