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

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

Neuron 654 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.8543. Min Act: -0.0000

Data Index: 1582408 (Python Code)

Max Activating Token Index: 154

Text #1

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.6312. Min Act: -0.0000

Data Index: 1594005 (Python Code)

Max Activating Token Index: 894

Text #2

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.7291. Min Act: -0.0000

Data Index: 1624746 (Python Code)

Max Activating Token Index: 593

Text #3

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.4499. Min Act: -0.0000

Data Index: 1531952 (Python Code)

Max Activating Token Index: 842

Text #4

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.5934. Min Act: -0.0000

Data Index: 1472823 (Python Code)

Max Activating Token Index: 926

Text #5

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.3730. Min Act: -0.0000

Data Index: 1564424 (Python Code)

Max Activating Token Index: 198

Text #6

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.5704. Min Act: -0.0000

Data Index: 1435122 (Python Code)

Max Activating Token Index: 79

Text #7

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.7039. Min Act: -0.0000

Data Index: 1597231 (Python Code)

Max Activating Token Index: 665

Text #8

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.5489. Min Act: -0.0000

Data Index: 1360135 (Python Code)

Max Activating Token Index: 59

Text #9

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.5078. Min Act: -0.0000

Data Index: 1643724 (Python Code)

Max Activating Token Index: 777

Text #10

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.4984. Min Act: -0.0000

Data Index: 1446617 (Python Code)

Max Activating Token Index: 655

Text #11

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.4649. Min Act: -0.0000

Data Index: 1486724 (Python Code)

Max Activating Token Index: 888

Text #12

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.2568. Min Act: -0.0000

Data Index: 1414769 (Python Code)

Max Activating Token Index: 235

Text #13

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.4293. Min Act: -0.0000

Data Index: 1370263 (Python Code)

Max Activating Token Index: 747

Text #14

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.4251. Min Act: -0.0000

Data Index: 1405473 (Python Code)

Max Activating Token Index: 328

Text #15

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.2580. Min Act: -0.0000

Data Index: 1492419 (Python Code)

Max Activating Token Index: 916

Text #16

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.0393. Min Act: -0.0000

Data Index: 1385496 (Python Code)

Max Activating Token Index: 290

Text #17

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.5655. Min Act: -0.0000

Data Index: 1546387 (Python Code)

Max Activating Token Index: 1006

Text #18

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.3657. Min Act: -0.0000

Data Index: 1433200 (Python Code)

Max Activating Token Index: 123

Text #19

Max Range: 4.8543. Min Range: -4.8543

Max Act: 4.1661. Min Act: -0.0000

Data Index: 1512571 (Python Code)

Max Activating Token Index: 944