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

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

Neuron 3386 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9625. Min Range: -4.9625

Max Act: 4.9625. Min Act: -0.0000

Data Index: 1573344 (Python Code)

Max Activating Token Index: 852

Text #1

Max Range: 4.9625. Min Range: -4.9625

Max Act: 4.6263. Min Act: -0.0000

Data Index: 1531953 (Python Code)

Max Activating Token Index: 63

Text #2

Max Range: 4.9625. Min Range: -4.9625

Max Act: 4.7568. Min Act: -0.0000

Data Index: 1363935 (Python Code)

Max Activating Token Index: 393

Text #3

Max Range: 4.9625. Min Range: -4.9625

Max Act: 4.6173. Min Act: -0.0000

Data Index: 1610147 (Python Code)

Max Activating Token Index: 700

Text #4

Max Range: 4.9625. Min Range: -4.9625

Max Act: 4.3056. Min Act: -0.0000

Data Index: 1484793 (Python Code)

Max Activating Token Index: 563

Text #5

Max Range: 4.9625. Min Range: -4.9625

Max Act: 4.2003. Min Act: -0.0000

Data Index: 1537008 (Python Code)

Max Activating Token Index: 892

Text #6

Max Range: 4.9625. Min Range: -4.9625

Max Act: 4.2026. Min Act: -0.0000

Data Index: 1504653 (Python Code)

Max Activating Token Index: 70

Text #7

Max Range: 4.9625. Min Range: -4.9625

Max Act: 4.5139. Min Act: -0.0000

Data Index: 1421232 (Python Code)

Max Activating Token Index: 795

Text #8

Max Range: 4.9625. Min Range: -4.9625

Max Act: 4.0199. Min Act: -0.0000

Data Index: 1484955 (Python Code)

Max Activating Token Index: 648

Text #9

Max Range: 4.9625. Min Range: -4.9625

Max Act: 3.7402. Min Act: -0.0000

Data Index: 1467587 (Python Code)

Max Activating Token Index: 643

Text #10

Max Range: 4.9625. Min Range: -4.9625

Max Act: 3.8968. Min Act: -0.0000

Data Index: 1443731 (Python Code)

Max Activating Token Index: 889

Text #11

Max Range: 4.9625. Min Range: -4.9625

Max Act: 3.8844. Min Act: -0.0000

Data Index: 1603555 (Python Code)

Max Activating Token Index: 909

Text #12

Max Range: 4.9625. Min Range: -4.9625

Max Act: 3.9355. Min Act: -0.0001

Data Index: 1528959 (Python Code)

Max Activating Token Index: 703

Text #13

Max Range: 4.9625. Min Range: -4.9625

Max Act: 3.7898. Min Act: -0.0000

Data Index: 1626299 (Python Code)

Max Activating Token Index: 436

Text #14

Max Range: 4.9625. Min Range: -4.9625

Max Act: 3.7253. Min Act: -0.0000

Data Index: 1558308 (Python Code)

Max Activating Token Index: 754

Text #15

Max Range: 4.9625. Min Range: -4.9625

Max Act: 3.7120. Min Act: -0.0000

Data Index: 1620969 (Python Code)

Max Activating Token Index: 41

Text #16

Max Range: 4.9625. Min Range: -4.9625

Max Act: 3.5249. Min Act: -0.0000

Data Index: 1509718 (Python Code)

Max Activating Token Index: 665

Text #17

Max Range: 4.9625. Min Range: -4.9625

Max Act: 3.4938. Min Act: -0.0000

Data Index: 1595480 (Python Code)

Max Activating Token Index: 845

Text #18

Max Range: 4.9625. Min Range: -4.9625

Max Act: 3.6524. Min Act: -0.0000

Data Index: 1503208 (Python Code)

Max Activating Token Index: 853

Text #19

Max Range: 4.9625. Min Range: -4.9625

Max Act: 3.4877. Min Act: -0.0000

Data Index: 1655059 (Python Code)

Max Activating Token Index: 46