Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2980 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.7510. Min Act: -0.0001

Data Index: 1515673 (Python Code)

Max Activating Token Index: 35

Text #1

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6861. Min Act: -0.0001

Data Index: 1456267 (Python Code)

Max Activating Token Index: 594

Text #2

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6712. Min Act: -0.0001

Data Index: 1393076 (Python Code)

Max Activating Token Index: 964

Text #3

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.7100. Min Act: -0.0001

Data Index: 1567469 (Python Code)

Max Activating Token Index: 589

Text #4

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.7134. Min Act: -0.0001

Data Index: 1456020 (Python Code)

Max Activating Token Index: 61

Text #5

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6068. Min Act: -0.0001

Data Index: 1456932 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6660. Min Act: -0.0001

Data Index: 1530174 (Python Code)

Max Activating Token Index: 304

Text #7

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5764. Min Act: -0.0001

Data Index: 1547255 (Python Code)

Max Activating Token Index: 134

Text #8

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6366. Min Act: -0.0001

Data Index: 1572949 (Python Code)

Max Activating Token Index: 805

Text #9

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5181. Min Act: -0.0001

Data Index: 1390301 (Python Code)

Max Activating Token Index: 755

Text #10

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6261. Min Act: -0.0001

Data Index: 1592898 (Python Code)

Max Activating Token Index: 123

Text #11

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6185. Min Act: -0.0001

Data Index: 1497701 (Python Code)

Max Activating Token Index: 69

Text #12

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.6185. Min Act: -0.0001

Data Index: 1600400 (Python Code)

Max Activating Token Index: 736

Text #13

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5469. Min Act: -0.0001

Data Index: 1492504 (Python Code)

Max Activating Token Index: 431

Text #14

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5773. Min Act: -0.0001

Data Index: 1481680 (Python Code)

Max Activating Token Index: 410

Text #15

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5754. Min Act: -0.0001

Data Index: 1492025 (Python Code)

Max Activating Token Index: 256

Text #16

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5546. Min Act: -0.0001

Data Index: 1541921 (Python Code)

Max Activating Token Index: 115

Text #17

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5513. Min Act: -0.0001

Data Index: 1604273 (Python Code)

Max Activating Token Index: 305

Text #18

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5863. Min Act: -0.0001

Data Index: 1599020 (Python Code)

Max Activating Token Index: 61

Text #19

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5730. Min Act: -0.0001

Data Index: 1573607 (Python Code)

Max Activating Token Index: 567