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

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

Neuron 4563 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2840. Min Range: -4.2840

Max Act: 4.2840. Min Act: -0.0000

Data Index: 1576221 (Python Code)

Max Activating Token Index: 328

Text #1

Max Range: 4.2840. Min Range: -4.2840

Max Act: 4.2635. Min Act: -0.0000

Data Index: 1462830 (Python Code)

Max Activating Token Index: 944

Text #2

Max Range: 4.2840. Min Range: -4.2840

Max Act: 4.1520. Min Act: -0.0000

Data Index: 1495222 (Python Code)

Max Activating Token Index: 211

Text #3

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.8219. Min Act: -0.0000

Data Index: 1567661 (Python Code)

Max Activating Token Index: 774

Text #4

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.9594. Min Act: -0.0000

Data Index: 1439919 (Python Code)

Max Activating Token Index: 689

Text #5

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.7568. Min Act: -0.0000

Data Index: 1654078 (Python Code)

Max Activating Token Index: 406

Text #6

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.7537. Min Act: -0.0000

Data Index: 1423994 (Python Code)

Max Activating Token Index: 569

Text #7

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.7152. Min Act: -0.0000

Data Index: 1414993 (Python Code)

Max Activating Token Index: 72

Text #8

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.7065. Min Act: -0.0000

Data Index: 1517061 (Python Code)

Max Activating Token Index: 312

Text #9

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.8636. Min Act: -0.0000

Data Index: 1464468 (Python Code)

Max Activating Token Index: 993

Text #10

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.5140. Min Act: -0.0000

Data Index: 1576216 (Python Code)

Max Activating Token Index: 706

Text #11

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.6540. Min Act: -0.0000

Data Index: 1414159 (Python Code)

Max Activating Token Index: 88

Text #12

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.3336. Min Act: -0.0000

Data Index: 1416005 (Python Code)

Max Activating Token Index: 335

Text #13

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.7530. Min Act: -0.0000

Data Index: 1634621 (Python Code)

Max Activating Token Index: 411

Text #14

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.2321. Min Act: -0.0000

Data Index: 1534331 (Python Code)

Max Activating Token Index: 354

Text #15

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.3901. Min Act: -0.0000

Data Index: 1383656 (Python Code)

Max Activating Token Index: 880

Text #16

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.5367. Min Act: -0.0000

Data Index: 1514097 (Python Code)

Max Activating Token Index: 427

Text #17

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.3510. Min Act: -0.0000

Data Index: 1452880 (Python Code)

Max Activating Token Index: 854

Text #18

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.5244. Min Act: -0.0000

Data Index: 1452389 (Python Code)

Max Activating Token Index: 626

Text #19

Max Range: 4.2840. Min Range: -4.2840

Max Act: 3.4837. Min Act: -0.0000

Data Index: 1405798 (Python Code)

Max Activating Token Index: 317