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

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

Neuron 390 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: 3.2844. Min Range: -3.2844

Max Act: 3.2844. Min Act: -0.0000

Data Index: 1389373 (Python Code)

Max Activating Token Index: 844

Text #1

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.9969. Min Act: -0.0000

Data Index: 1579508 (Python Code)

Max Activating Token Index: 339

Text #2

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.9632. Min Act: -0.0000

Data Index: 1455226 (Python Code)

Max Activating Token Index: 1014

Text #3

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.9359. Min Act: -0.0000

Data Index: 383932 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.6374. Min Act: -0.0000

Data Index: 1431906 (Python Code)

Max Activating Token Index: 760

Text #5

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.5984. Min Act: -0.0000

Data Index: 1473886 (Python Code)

Max Activating Token Index: 584

Text #6

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.5398. Min Act: -0.0000

Data Index: 1481187 (Python Code)

Max Activating Token Index: 578

Text #7

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.5040. Min Act: -0.0000

Data Index: 1495518 (Python Code)

Max Activating Token Index: 539

Text #8

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.4586. Min Act: -0.0000

Data Index: 1561088 (Python Code)

Max Activating Token Index: 635

Text #9

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.4390. Min Act: -0.0000

Data Index: 1383149 (Python Code)

Max Activating Token Index: 434

Text #10

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.4307. Min Act: -0.0000

Data Index: 1572323 (Python Code)

Max Activating Token Index: 253

Text #11

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.3848. Min Act: -0.0000

Data Index: 1366557 (Python Code)

Max Activating Token Index: 59

Text #12

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.3928. Min Act: -0.0000

Data Index: 1531627 (Python Code)

Max Activating Token Index: 708

Text #13

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.2484. Min Act: -0.0000

Data Index: 1436385 (Python Code)

Max Activating Token Index: 867

Text #14

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.3120. Min Act: -0.0000

Data Index: 1594208 (Python Code)

Max Activating Token Index: 926

Text #15

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.2876. Min Act: -0.0000

Data Index: 1564687 (Python Code)

Max Activating Token Index: 69

Text #16

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.2647. Min Act: -0.0000

Data Index: 1571422 (Python Code)

Max Activating Token Index: 55

Text #17

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.1895. Min Act: -0.0000

Data Index: 1514943 (Python Code)

Max Activating Token Index: 632

Text #18

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.1768. Min Act: -0.0000

Data Index: 1444918 (Python Code)

Max Activating Token Index: 703

Text #19

Max Range: 3.2844. Min Range: -3.2844

Max Act: 2.1626. Min Act: -0.0000

Data Index: 1523538 (Python Code)

Max Activating Token Index: 524