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

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

Neuron 1233 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.7424. Min Act: -0.0001

Data Index: 1607803 (Python Code)

Max Activating Token Index: 439

Text #1

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.7195. Min Act: -0.0001

Data Index: 1556780 (Python Code)

Max Activating Token Index: 101

Text #2

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6711. Min Act: -0.0001

Data Index: 1552444 (Python Code)

Max Activating Token Index: 16

Text #3

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.7106. Min Act: -0.0001

Data Index: 1481036 (Python Code)

Max Activating Token Index: 244

Text #4

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6652. Min Act: -0.0001

Data Index: 1532011 (Python Code)

Max Activating Token Index: 608

Text #5

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1449179 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1643236 (Python Code)

Max Activating Token Index: 49

Text #7

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5690. Min Act: -0.0001

Data Index: 1429565 (Python Code)

Max Activating Token Index: 143

Text #8

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6639. Min Act: -0.0001

Data Index: 1373275 (Python Code)

Max Activating Token Index: 233

Text #9

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6264. Min Act: -0.0001

Data Index: 1368280 (Python Code)

Max Activating Token Index: 465

Text #10

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6588. Min Act: -0.0001

Data Index: 1558620 (Python Code)

Max Activating Token Index: 886

Text #11

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6154. Min Act: -0.0001

Data Index: 1383200 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6125. Min Act: -0.0001

Data Index: 1544710 (Python Code)

Max Activating Token Index: 659

Text #13

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6341. Min Act: -0.0001

Data Index: 1520740 (Python Code)

Max Activating Token Index: 510

Text #14

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6926. Min Act: -0.0001

Data Index: 1652917 (Python Code)

Max Activating Token Index: 351

Text #15

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5986. Min Act: -0.0001

Data Index: 1557523 (Python Code)

Max Activating Token Index: 436

Text #16

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5868. Min Act: -0.0001

Data Index: 1588366 (Python Code)

Max Activating Token Index: 822

Text #17

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.6320. Min Act: -0.0001

Data Index: 1542807 (Python Code)

Max Activating Token Index: 700

Text #18

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1438040 (Python Code)

Max Activating Token Index: 754

Text #19

Max Range: 0.7424. Min Range: -0.7424

Max Act: 0.5986. Min Act: -0.0001

Data Index: 1654707 (Python Code)

Max Activating Token Index: 599