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

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

Neuron 5371 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: 2.6963. Min Range: -2.6963

Max Act: 2.6963. Min Act: -0.0000

Data Index: 1401323 (Python Code)

Max Activating Token Index: 385

Text #1

Max Range: 2.6963. Min Range: -2.6963

Max Act: 2.4611. Min Act: -0.0000

Data Index: 1447320 (Python Code)

Max Activating Token Index: 1021

Text #2

Max Range: 2.6963. Min Range: -2.6963

Max Act: 2.0420. Min Act: -0.0000

Data Index: 1558810 (Python Code)

Max Activating Token Index: 466

Text #3

Max Range: 2.6963. Min Range: -2.6963

Max Act: 2.1371. Min Act: -0.0000

Data Index: 1548776 (Python Code)

Max Activating Token Index: 385

Text #4

Max Range: 2.6963. Min Range: -2.6963

Max Act: 2.1262. Min Act: -0.0000

Data Index: 1397330 (Python Code)

Max Activating Token Index: 964

Text #5

Max Range: 2.6963. Min Range: -2.6963

Max Act: 2.1058. Min Act: -0.0000

Data Index: 1575747 (Python Code)

Max Activating Token Index: 745

Text #6

Max Range: 2.6963. Min Range: -2.6963

Max Act: 1.9558. Min Act: -0.0000

Data Index: 1582688 (Python Code)

Max Activating Token Index: 515

Text #7

Max Range: 2.6963. Min Range: -2.6963

Max Act: 2.1995. Min Act: -0.0000

Data Index: 1648296 (Python Code)

Max Activating Token Index: 910

Text #8

Max Range: 2.6963. Min Range: -2.6963

Max Act: 2.1744. Min Act: -0.0000

Data Index: 1553697 (Python Code)

Max Activating Token Index: 756

Text #9

Max Range: 2.6963. Min Range: -2.6963

Max Act: 2.0318. Min Act: -0.0000

Data Index: 1626881 (Python Code)

Max Activating Token Index: 206

Text #10

Max Range: 2.6963. Min Range: -2.6963

Max Act: 2.0330. Min Act: -0.0000

Data Index: 1440415 (Python Code)

Max Activating Token Index: 53

Text #11

Max Range: 2.6963. Min Range: -2.6963

Max Act: 1.9491. Min Act: -0.0000

Data Index: 1523760 (Python Code)

Max Activating Token Index: 924

Text #12

Max Range: 2.6963. Min Range: -2.6963

Max Act: 1.9308. Min Act: -0.0000

Data Index: 1485567 (Python Code)

Max Activating Token Index: 482

Text #13

Max Range: 2.6963. Min Range: -2.6963

Max Act: 1.8876. Min Act: -0.0000

Data Index: 1482811 (Python Code)

Max Activating Token Index: 62

Text #14

Max Range: 2.6963. Min Range: -2.6963

Max Act: 1.6728. Min Act: -0.0000

Data Index: 1405471 (Python Code)

Max Activating Token Index: 344

Text #15

Max Range: 2.6963. Min Range: -2.6963

Max Act: 1.8699. Min Act: -0.0000

Data Index: 1554605 (Python Code)

Max Activating Token Index: 590

Text #16

Max Range: 2.6963. Min Range: -2.6963

Max Act: 1.7688. Min Act: -0.0000

Data Index: 1483525 (Python Code)

Max Activating Token Index: 821

Text #17

Max Range: 2.6963. Min Range: -2.6963

Max Act: 1.8544. Min Act: -0.0000

Data Index: 1383025 (Python Code)

Max Activating Token Index: 92

Text #18

Max Range: 2.6963. Min Range: -2.6963

Max Act: 1.7579. Min Act: -0.0000

Data Index: 1531169 (Python Code)

Max Activating Token Index: 114

Text #19

Max Range: 2.6963. Min Range: -2.6963

Max Act: 1.8455. Min Act: -0.0000

Data Index: 1523957 (Python Code)

Max Activating Token Index: 619