Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4099 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.6601. Min Act: -0.0000

Data Index: 1604178 (Python Code)

Max Activating Token Index: 502

Text #1

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.6164. Min Act: -0.0000

Data Index: 1610128 (Python Code)

Max Activating Token Index: 710

Text #2

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.5542. Min Act: -0.0000

Data Index: 1426835 (Python Code)

Max Activating Token Index: 36

Text #3

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.4991. Min Act: -0.0000

Data Index: 1512708 (Python Code)

Max Activating Token Index: 842

Text #4

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.5236. Min Act: -0.0000

Data Index: 1515864 (Python Code)

Max Activating Token Index: 732

Text #5

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.4875. Min Act: -0.0000

Data Index: 1637204 (Python Code)

Max Activating Token Index: 26

Text #6

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.4838. Min Act: -0.0000

Data Index: 1464857 (Python Code)

Max Activating Token Index: 75

Text #7

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.5961. Min Act: -0.0000

Data Index: 1537425 (Python Code)

Max Activating Token Index: 603

Text #8

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.5806. Min Act: -0.0000

Data Index: 1609603 (Python Code)

Max Activating Token Index: 1005

Text #9

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.5738. Min Act: -0.0000

Data Index: 1448252 (Python Code)

Max Activating Token Index: 93

Text #10

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.4329. Min Act: -0.0000

Data Index: 1361056 (Python Code)

Max Activating Token Index: 60

Text #11

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.3974. Min Act: -0.0000

Data Index: 1427086 (Python Code)

Max Activating Token Index: 43

Text #12

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.5679. Min Act: -0.0000

Data Index: 1608874 (Python Code)

Max Activating Token Index: 48

Text #13

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.4650. Min Act: -0.0000

Data Index: 1383853 (Python Code)

Max Activating Token Index: 581

Text #14

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.4755. Min Act: -0.0000

Data Index: 1655685 (Python Code)

Max Activating Token Index: 81

Text #15

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.4298. Min Act: -0.0000

Data Index: 1568138 (Python Code)

Max Activating Token Index: 177

Text #16

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.3729. Min Act: -0.0000

Data Index: 1619876 (Python Code)

Max Activating Token Index: 712

Text #17

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.3642. Min Act: -0.0000

Data Index: 1397322 (Python Code)

Max Activating Token Index: 834

Text #18

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.4137. Min Act: -0.0000

Data Index: 1395354 (Python Code)

Max Activating Token Index: 73

Text #19

Max Range: 1.6601. Min Range: -1.6601

Max Act: 1.4066. Min Act: -0.0000

Data Index: 1646633 (Python Code)

Max Activating Token Index: 894