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

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

Neuron 2806 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4309. Min Range: -2.4309

Max Act: 2.4309. Min Act: -0.0000

Data Index: 1622614 (Python Code)

Max Activating Token Index: 618

Text #1

Max Range: 2.4309. Min Range: -2.4309

Max Act: 2.1635. Min Act: -0.0000

Data Index: 1522629 (Python Code)

Max Activating Token Index: 997

Text #2

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.7746. Min Act: -0.0000

Data Index: 1439342 (Python Code)

Max Activating Token Index: 203

Text #3

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.8894. Min Act: -0.0000

Data Index: 1619764 (Python Code)

Max Activating Token Index: 66

Text #4

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.6860. Min Act: -0.0000

Data Index: 1510197 (Python Code)

Max Activating Token Index: 667

Text #5

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.8633. Min Act: -0.0000

Data Index: 1563871 (Python Code)

Max Activating Token Index: 551

Text #6

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.6261. Min Act: -0.0000

Data Index: 1615733 (Python Code)

Max Activating Token Index: 665

Text #7

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.6317. Min Act: -0.0000

Data Index: 1618233 (Python Code)

Max Activating Token Index: 233

Text #8

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.5977. Min Act: -0.0000

Data Index: 1579567 (Python Code)

Max Activating Token Index: 908

Text #9

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.6779. Min Act: -0.0000

Data Index: 1629734 (Python Code)

Max Activating Token Index: 304

Text #10

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.4998. Min Act: -0.0000

Data Index: 1610535 (Python Code)

Max Activating Token Index: 249

Text #11

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.5078. Min Act: -0.0000

Data Index: 1611478 (Python Code)

Max Activating Token Index: 278

Text #12

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.6583. Min Act: -0.0000

Data Index: 1539295 (Python Code)

Max Activating Token Index: 630

Text #13

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.5553. Min Act: -0.0000

Data Index: 1398665 (Python Code)

Max Activating Token Index: 408

Text #14

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.3469. Min Act: -0.0000

Data Index: 1615399 (Python Code)

Max Activating Token Index: 899

Text #15

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.5128. Min Act: -0.0000

Data Index: 1515337 (Python Code)

Max Activating Token Index: 145

Text #16

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.6098. Min Act: -0.0000

Data Index: 1465812 (Python Code)

Max Activating Token Index: 324

Text #17

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.5049. Min Act: -0.0000

Data Index: 1450754 (Python Code)

Max Activating Token Index: 1017

Text #18

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.6046. Min Act: -0.0000

Data Index: 1527869 (Python Code)

Max Activating Token Index: 299

Text #19

Max Range: 2.4309. Min Range: -2.4309

Max Act: 1.4921. Min Act: -0.0000

Data Index: 1526295 (Python Code)

Max Activating Token Index: 188