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

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

Neuron 2417 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: 3.2392. Min Range: -3.2392

Max Act: 3.2392. Min Act: -0.0000

Data Index: 1431980 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.8333. Min Act: -0.0000

Data Index: 1396712 (Python Code)

Max Activating Token Index: 683

Text #2

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.8138. Min Act: -0.0000

Data Index: 1571845 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.6672. Min Act: -0.0000

Data Index: 1423255 (Python Code)

Max Activating Token Index: 574

Text #4

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.7475. Min Act: -0.0000

Data Index: 1621420 (Python Code)

Max Activating Token Index: 28

Text #5

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.8741. Min Act: -0.0000

Data Index: 1546551 (Python Code)

Max Activating Token Index: 319

Text #6

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.7207. Min Act: -0.0000

Data Index: 1472846 (Python Code)

Max Activating Token Index: 879

Text #7

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.5750. Min Act: -0.0000

Data Index: 1507871 (Python Code)

Max Activating Token Index: 191

Text #8

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.7834. Min Act: -0.0000

Data Index: 1498596 (Python Code)

Max Activating Token Index: 198

Text #9

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.6489. Min Act: -0.0000

Data Index: 1533148 (Python Code)

Max Activating Token Index: 438

Text #10

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.6345. Min Act: -0.0000

Data Index: 1590521 (Python Code)

Max Activating Token Index: 305

Text #11

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.7281. Min Act: -0.0000

Data Index: 1563085 (Python Code)

Max Activating Token Index: 633

Text #12

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.6034. Min Act: -0.0000

Data Index: 1573627 (Python Code)

Max Activating Token Index: 831

Text #13

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.5972. Min Act: -0.0000

Data Index: 1571501 (Python Code)

Max Activating Token Index: 239

Text #14

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.5877. Min Act: -0.0000

Data Index: 1620990 (Python Code)

Max Activating Token Index: 884

Text #15

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.6024. Min Act: -0.0000

Data Index: 1563171 (Python Code)

Max Activating Token Index: 661

Text #16

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.5791. Min Act: -0.0000

Data Index: 1481017 (Python Code)

Max Activating Token Index: 527

Text #17

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.4569. Min Act: -0.0000

Data Index: 1635112 (Python Code)

Max Activating Token Index: 160

Text #18

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.5321. Min Act: -0.0000

Data Index: 1415763 (Python Code)

Max Activating Token Index: 44

Text #19

Max Range: 3.2392. Min Range: -3.2392

Max Act: 2.6408. Min Act: -0.0000

Data Index: 1642212 (Python Code)

Max Activating Token Index: 619