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

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

Neuron 3059 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5966. Min Range: -2.5966

Max Act: 2.5966. Min Act: -0.0000

Data Index: 1547747 (Python Code)

Max Activating Token Index: 311

Text #1

Max Range: 2.5966. Min Range: -2.5966

Max Act: 2.2430. Min Act: -0.0000

Data Index: 1507069 (Python Code)

Max Activating Token Index: 592

Text #2

Max Range: 2.5966. Min Range: -2.5966

Max Act: 2.1563. Min Act: -0.0000

Data Index: 1511181 (Python Code)

Max Activating Token Index: 592

Text #3

Max Range: 2.5966. Min Range: -2.5966

Max Act: 2.1103. Min Act: -0.0000

Data Index: 1380089 (Python Code)

Max Activating Token Index: 113

Text #4

Max Range: 2.5966. Min Range: -2.5966

Max Act: 2.2787. Min Act: -0.0000

Data Index: 1553601 (Python Code)

Max Activating Token Index: 205

Text #5

Max Range: 2.5966. Min Range: -2.5966

Max Act: 2.1482. Min Act: -0.0000

Data Index: 1397729 (Python Code)

Max Activating Token Index: 761

Text #6

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.9370. Min Act: -0.0000

Data Index: 1495292 (Python Code)

Max Activating Token Index: 596

Text #7

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.9871. Min Act: -0.0000

Data Index: 1362029 (Python Code)

Max Activating Token Index: 771

Text #8

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.8582. Min Act: -0.0000

Data Index: 1525617 (Python Code)

Max Activating Token Index: 317

Text #9

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.8266. Min Act: -0.0000

Data Index: 1599792 (Python Code)

Max Activating Token Index: 661

Text #10

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.9650. Min Act: -0.0000

Data Index: 1369848 (Python Code)

Max Activating Token Index: 646

Text #11

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.9674. Min Act: -0.0000

Data Index: 1473700 (Python Code)

Max Activating Token Index: 559

Text #12

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.8543. Min Act: -0.0000

Data Index: 1564691 (Python Code)

Max Activating Token Index: 413

Text #13

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.9447. Min Act: -0.0000

Data Index: 1623701 (Python Code)

Max Activating Token Index: 920

Text #14

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.7312. Min Act: -0.0000

Data Index: 1489315 (Python Code)

Max Activating Token Index: 504

Text #15

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.6989. Min Act: -0.0000

Data Index: 1540765 (Python Code)

Max Activating Token Index: 839

Text #16

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.7736. Min Act: -0.0000

Data Index: 1562549 (Python Code)

Max Activating Token Index: 51

Text #17

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.5734. Min Act: -0.0000

Data Index: 1492922 (Python Code)

Max Activating Token Index: 521

Text #18

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.7329. Min Act: -0.0000

Data Index: 1531228 (Python Code)

Max Activating Token Index: 158

Text #19

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.5996. Min Act: -0.0000

Data Index: 1420315 (Python Code)

Max Activating Token Index: 344