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

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

Neuron 1398 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8314. Min Range: -3.8314

Max Act: 3.8314. Min Act: -0.0000

Data Index: 1445809 (Python Code)

Max Activating Token Index: 435

Text #1

Max Range: 3.8314. Min Range: -3.8314

Max Act: 3.3885. Min Act: -0.0000

Data Index: 1564950 (Python Code)

Max Activating Token Index: 306

Text #2

Max Range: 3.8314. Min Range: -3.8314

Max Act: 3.5742. Min Act: -0.0000

Data Index: 1439131 (Python Code)

Max Activating Token Index: 601

Text #3

Max Range: 3.8314. Min Range: -3.8314

Max Act: 2.2897. Min Act: -0.0000

Data Index: 1472727 (Python Code)

Max Activating Token Index: 1009

Text #4

Max Range: 3.8314. Min Range: -3.8314

Max Act: 2.2148. Min Act: -0.0000

Data Index: 1503212 (Python Code)

Max Activating Token Index: 561

Text #5

Max Range: 3.8314. Min Range: -3.8314

Max Act: 2.1642. Min Act: -0.0000

Data Index: 1504222 (Python Code)

Max Activating Token Index: 194

Text #6

Max Range: 3.8314. Min Range: -3.8314

Max Act: 2.2618. Min Act: -0.0000

Data Index: 1586034 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 3.8314. Min Range: -3.8314

Max Act: 2.1557. Min Act: -0.0000

Data Index: 1555999 (Python Code)

Max Activating Token Index: 767

Text #8

Max Range: 3.8314. Min Range: -3.8314

Max Act: 2.0724. Min Act: -0.0000

Data Index: 1533739 (Python Code)

Max Activating Token Index: 864

Text #9

Max Range: 3.8314. Min Range: -3.8314

Max Act: 2.1698. Min Act: -0.0000

Data Index: 1407825 (Python Code)

Max Activating Token Index: 777

Text #10

Max Range: 3.8314. Min Range: -3.8314

Max Act: 2.1545. Min Act: -0.0000

Data Index: 1413410 (Python Code)

Max Activating Token Index: 657

Text #11

Max Range: 3.8314. Min Range: -3.8314

Max Act: 2.1693. Min Act: -0.0000

Data Index: 1641263 (Python Code)

Max Activating Token Index: 445

Text #12

Max Range: 3.8314. Min Range: -3.8314

Max Act: 2.2639. Min Act: -0.0000

Data Index: 1591347 (Python Code)

Max Activating Token Index: 1002

Text #13

Max Range: 3.8314. Min Range: -3.8314

Max Act: 2.0397. Min Act: -0.0000

Data Index: 1585810 (Python Code)

Max Activating Token Index: 861

Text #14

Max Range: 3.8314. Min Range: -3.8314

Max Act: 2.1207. Min Act: -0.0000

Data Index: 1426197 (Python Code)

Max Activating Token Index: 837

Text #15

Max Range: 3.8314. Min Range: -3.8314

Max Act: 2.0072. Min Act: -0.0000

Data Index: 1568717 (Python Code)

Max Activating Token Index: 64

Text #16

Max Range: 3.8314. Min Range: -3.8314

Max Act: 2.2174. Min Act: -0.0000

Data Index: 1517097 (Python Code)

Max Activating Token Index: 499

Text #17

Max Range: 3.8314. Min Range: -3.8314

Max Act: 2.1003. Min Act: -0.0000

Data Index: 1498679 (Python Code)

Max Activating Token Index: 208

Text #18

Max Range: 3.8314. Min Range: -3.8314

Max Act: 2.0934. Min Act: -0.0000

Data Index: 1476220 (Python Code)

Max Activating Token Index: 806

Text #19

Max Range: 3.8314. Min Range: -3.8314

Max Act: 2.0017. Min Act: -0.0000

Data Index: 1450042 (Python Code)

Max Activating Token Index: 707