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

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

Neuron 4855 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: 1.4766. Min Range: -1.4766

Max Act: 1.4766. Min Act: -0.0000

Data Index: 1497481 (Python Code)

Max Activating Token Index: 940

Text #1

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.4170. Min Act: -0.0000

Data Index: 1555818 (Python Code)

Max Activating Token Index: 347

Text #2

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.3154. Min Act: -0.0000

Data Index: 1534937 (Python Code)

Max Activating Token Index: 42

Text #3

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.2632. Min Act: -0.0000

Data Index: 1621280 (Python Code)

Max Activating Token Index: 856

Text #4

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.2841. Min Act: -0.0000

Data Index: 1619694 (Python Code)

Max Activating Token Index: 617

Text #5

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.3012. Min Act: -0.0000

Data Index: 1529825 (Python Code)

Max Activating Token Index: 401

Text #6

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.2520. Min Act: -0.0000

Data Index: 1391539 (Python Code)

Max Activating Token Index: 46

Text #7

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.2305. Min Act: -0.0000

Data Index: 1653824 (Python Code)

Max Activating Token Index: 365

Text #8

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.2319. Min Act: -0.0000

Data Index: 1543363 (Python Code)

Max Activating Token Index: 571

Text #9

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.2024. Min Act: -0.0000

Data Index: 1611799 (Python Code)

Max Activating Token Index: 440

Text #10

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.2518. Min Act: -0.0000

Data Index: 1638114 (Python Code)

Max Activating Token Index: 248

Text #11

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.2110. Min Act: -0.0000

Data Index: 1504512 (Python Code)

Max Activating Token Index: 832

Text #12

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.1971. Min Act: -0.0000

Data Index: 1499333 (Python Code)

Max Activating Token Index: 682

Text #13

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.1799. Min Act: -0.0000

Data Index: 1573153 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.1336. Min Act: -0.0000

Data Index: 1587077 (Python Code)

Max Activating Token Index: 614

Text #15

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.1741. Min Act: -0.0000

Data Index: 1621871 (Python Code)

Max Activating Token Index: 837

Text #16

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.1686. Min Act: -0.0000

Data Index: 1494778 (Python Code)

Max Activating Token Index: 445

Text #17

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.1352. Min Act: -0.0000

Data Index: 1512160 (Python Code)

Max Activating Token Index: 698

Text #18

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.1964. Min Act: -0.0000

Data Index: 1466949 (Python Code)

Max Activating Token Index: 998

Text #19

Max Range: 1.4766. Min Range: -1.4766

Max Act: 1.1525. Min Act: -0.0000

Data Index: 1432633 (Python Code)

Max Activating Token Index: 639