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

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

Neuron 1489 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: 2.7816. Min Range: -2.7816

Max Act: 2.7816. Min Act: -0.0000

Data Index: 1549039 (Python Code)

Max Activating Token Index: 34

Text #1

Max Range: 2.7816. Min Range: -2.7816

Max Act: 2.6282. Min Act: -0.0000

Data Index: 1557168 (Python Code)

Max Activating Token Index: 315

Text #2

Max Range: 2.7816. Min Range: -2.7816

Max Act: 2.7446. Min Act: -0.0000

Data Index: 1386708 (Python Code)

Max Activating Token Index: 661

Text #3

Max Range: 2.7816. Min Range: -2.7816

Max Act: 2.2308. Min Act: -0.0000

Data Index: 1616959 (Python Code)

Max Activating Token Index: 804

Text #4

Max Range: 2.7816. Min Range: -2.7816

Max Act: 2.2963. Min Act: -0.0000

Data Index: 1458450 (Python Code)

Max Activating Token Index: 613

Text #5

Max Range: 2.7816. Min Range: -2.7816

Max Act: 2.2832. Min Act: -0.0000

Data Index: 1460033 (Python Code)

Max Activating Token Index: 722

Text #6

Max Range: 2.7816. Min Range: -2.7816

Max Act: 2.0474. Min Act: -0.0000

Data Index: 1653232 (Python Code)

Max Activating Token Index: 104

Text #7

Max Range: 2.7816. Min Range: -2.7816

Max Act: 2.0890. Min Act: -0.0000

Data Index: 1437763 (Python Code)

Max Activating Token Index: 75

Text #8

Max Range: 2.7816. Min Range: -2.7816

Max Act: 1.9596. Min Act: -0.0000

Data Index: 1548432 (Python Code)

Max Activating Token Index: 604

Text #9

Max Range: 2.7816. Min Range: -2.7816

Max Act: 2.0429. Min Act: -0.0000

Data Index: 1549867 (Python Code)

Max Activating Token Index: 515

Text #10

Max Range: 2.7816. Min Range: -2.7816

Max Act: 1.9284. Min Act: -0.0000

Data Index: 1582605 (Python Code)

Max Activating Token Index: 464

Text #11

Max Range: 2.7816. Min Range: -2.7816

Max Act: 1.6941. Min Act: -0.0000

Data Index: 1539486 (Python Code)

Max Activating Token Index: 302

Text #12

Max Range: 2.7816. Min Range: -2.7816

Max Act: 1.7831. Min Act: -0.0000

Data Index: 1606529 (Python Code)

Max Activating Token Index: 124

Text #13

Max Range: 2.7816. Min Range: -2.7816

Max Act: 1.6282. Min Act: -0.0000

Data Index: 1645352 (Python Code)

Max Activating Token Index: 981

Text #14

Max Range: 2.7816. Min Range: -2.7816

Max Act: 1.5818. Min Act: -0.0000

Data Index: 1543420 (Python Code)

Max Activating Token Index: 999

Text #15

Max Range: 2.7816. Min Range: -2.7816

Max Act: 1.6754. Min Act: -0.0000

Data Index: 1456932 (Python Code)

Max Activating Token Index: 133

Text #16

Max Range: 2.7816. Min Range: -2.7816

Max Act: 1.6877. Min Act: -0.0000

Data Index: 1499476 (Python Code)

Max Activating Token Index: 981

Text #17

Max Range: 2.7816. Min Range: -2.7816

Max Act: 1.6308. Min Act: -0.0000

Data Index: 1604301 (Python Code)

Max Activating Token Index: 959

Text #18

Max Range: 2.7816. Min Range: -2.7816

Max Act: 1.4570. Min Act: -0.0000

Data Index: 1439277 (Python Code)

Max Activating Token Index: 853

Text #19

Max Range: 2.7816. Min Range: -2.7816

Max Act: 1.6154. Min Act: -0.0000

Data Index: 1434412 (Python Code)

Max Activating Token Index: 463