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

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

Neuron 5078 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: 2.2208. Min Range: -2.2208

Max Act: 2.0141. Min Act: -0.0000

Data Index: 1568036 (Python Code)

Max Activating Token Index: 572

Text #1

Max Range: 2.2208. Min Range: -2.2208

Max Act: 2.2208. Min Act: -0.0000

Data Index: 1507251 (Python Code)

Max Activating Token Index: 27

Text #2

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.8960. Min Act: -0.0000

Data Index: 1610474 (Python Code)

Max Activating Token Index: 319

Text #3

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.8908. Min Act: -0.0000

Data Index: 1472926 (Python Code)

Max Activating Token Index: 170

Text #4

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.8593. Min Act: -0.0000

Data Index: 1443638 (Python Code)

Max Activating Token Index: 67

Text #5

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.8283. Min Act: -0.0000

Data Index: 1361386 (Python Code)

Max Activating Token Index: 514

Text #6

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.6275. Min Act: -0.0000

Data Index: 1383898 (Python Code)

Max Activating Token Index: 751

Text #7

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.8053. Min Act: -0.0000

Data Index: 1410599 (Python Code)

Max Activating Token Index: 68

Text #8

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.6951. Min Act: -0.0000

Data Index: 1510897 (Python Code)

Max Activating Token Index: 489

Text #9

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.8741. Min Act: -0.0000

Data Index: 1386778 (Python Code)

Max Activating Token Index: 360

Text #10

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.7899. Min Act: -0.0000

Data Index: 1630112 (Python Code)

Max Activating Token Index: 766

Text #11

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.7310. Min Act: -0.0000

Data Index: 1646853 (Python Code)

Max Activating Token Index: 597

Text #12

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.7670. Min Act: -0.0000

Data Index: 1512236 (Python Code)

Max Activating Token Index: 736

Text #13

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.6259. Min Act: -0.0000

Data Index: 1367247 (Python Code)

Max Activating Token Index: 139

Text #14

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.7080. Min Act: -0.0000

Data Index: 1474707 (Python Code)

Max Activating Token Index: 129

Text #15

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.9131. Min Act: -0.0000

Data Index: 1605086 (Python Code)

Max Activating Token Index: 231

Text #16

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.6270. Min Act: -0.0000

Data Index: 1579540 (Python Code)

Max Activating Token Index: 35

Text #17

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.7160. Min Act: -0.0000

Data Index: 1406592 (Python Code)

Max Activating Token Index: 961

Text #18

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.7852. Min Act: -0.0000

Data Index: 1612548 (Python Code)

Max Activating Token Index: 256

Text #19

Max Range: 2.2208. Min Range: -2.2208

Max Act: 1.5985. Min Act: -0.0000

Data Index: 1475693 (Python Code)

Max Activating Token Index: 283