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

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

Neuron 4211 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: 2.3873. Min Range: -2.3873

Max Act: 2.0328. Min Act: -0.0001

Data Index: 1510254 (Python Code)

Max Activating Token Index: 825

Text #1

Max Range: 2.3873. Min Range: -2.3873

Max Act: 2.2534. Min Act: -0.0000

Data Index: 1465778 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 2.3873. Min Range: -2.3873

Max Act: 2.2198. Min Act: -0.0001

Data Index: 1472991 (Python Code)

Max Activating Token Index: 629

Text #3

Max Range: 2.3873. Min Range: -2.3873

Max Act: 2.2830. Min Act: -0.0001

Data Index: 1396344 (Python Code)

Max Activating Token Index: 108

Text #4

Max Range: 2.3873. Min Range: -2.3873

Max Act: 2.3873. Min Act: -0.0000

Data Index: 1605640 (Python Code)

Max Activating Token Index: 594

Text #5

Max Range: 2.3873. Min Range: -2.3873

Max Act: 2.3136. Min Act: -0.0000

Data Index: 1648136 (Python Code)

Max Activating Token Index: 810

Text #6

Max Range: 2.3873. Min Range: -2.3873

Max Act: 2.0008. Min Act: -0.0000

Data Index: 1630518 (Python Code)

Max Activating Token Index: 245

Text #7

Max Range: 2.3873. Min Range: -2.3873

Max Act: 1.9769. Min Act: -0.0001

Data Index: 1458910 (Python Code)

Max Activating Token Index: 684

Text #8

Max Range: 2.3873. Min Range: -2.3873

Max Act: 2.0853. Min Act: -0.0001

Data Index: 1449624 (Python Code)

Max Activating Token Index: 495

Text #9

Max Range: 2.3873. Min Range: -2.3873

Max Act: 1.9558. Min Act: -0.0000

Data Index: 1435508 (Python Code)

Max Activating Token Index: 580

Text #10

Max Range: 2.3873. Min Range: -2.3873

Max Act: 1.7783. Min Act: -0.0000

Data Index: 1395384 (Python Code)

Max Activating Token Index: 619

Text #11

Max Range: 2.3873. Min Range: -2.3873

Max Act: 1.7708. Min Act: -0.0000

Data Index: 1421356 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 2.3873. Min Range: -2.3873

Max Act: 1.8698. Min Act: -0.0001

Data Index: 1447822 (Python Code)

Max Activating Token Index: 102

Text #13

Max Range: 2.3873. Min Range: -2.3873

Max Act: 1.7524. Min Act: -0.0001

Data Index: 1656608 (Python Code)

Max Activating Token Index: 766

Text #14

Max Range: 2.3873. Min Range: -2.3873

Max Act: 1.7366. Min Act: -0.0000

Data Index: 1610158 (Python Code)

Max Activating Token Index: 353

Text #15

Max Range: 2.3873. Min Range: -2.3873

Max Act: 1.6074. Min Act: -0.0001

Data Index: 1514726 (Python Code)

Max Activating Token Index: 286

Text #16

Max Range: 2.3873. Min Range: -2.3873

Max Act: 1.5251. Min Act: -0.0000

Data Index: 1598608 (Python Code)

Max Activating Token Index: 133

Text #17

Max Range: 2.3873. Min Range: -2.3873

Max Act: 1.4716. Min Act: -0.0000

Data Index: 1516399 (Python Code)

Max Activating Token Index: 326

Text #18

Max Range: 2.3873. Min Range: -2.3873

Max Act: 1.5174. Min Act: -0.0000

Data Index: 1408915 (Python Code)

Max Activating Token Index: 230

Text #19

Max Range: 2.3873. Min Range: -2.3873

Max Act: 1.5871. Min Act: -0.0000

Data Index: 1372076 (Python Code)

Max Activating Token Index: 687