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

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

Neuron 5830 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: 3.9610. Min Range: -3.9610

Max Act: 3.6279. Min Act: -0.0001

Data Index: 1649118 (Python Code)

Max Activating Token Index: 860

Text #1

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.9610. Min Act: -0.0001

Data Index: 1491019 (Python Code)

Max Activating Token Index: 772

Text #2

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.2330. Min Act: -0.0001

Data Index: 1534193 (Python Code)

Max Activating Token Index: 217

Text #3

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.6921. Min Act: -0.0001

Data Index: 1406398 (Python Code)

Max Activating Token Index: 486

Text #4

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.6643. Min Act: -0.0001

Data Index: 1592254 (Python Code)

Max Activating Token Index: 600

Text #5

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.3595. Min Act: -0.0001

Data Index: 1432323 (Python Code)

Max Activating Token Index: 726

Text #6

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.2282. Min Act: -0.0001

Data Index: 1619121 (Python Code)

Max Activating Token Index: 322

Text #7

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.6550. Min Act: -0.0001

Data Index: 1612788 (Python Code)

Max Activating Token Index: 112

Text #8

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.6678. Min Act: -0.0001

Data Index: 1451799 (Python Code)

Max Activating Token Index: 613

Text #9

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.6790. Min Act: -0.0001

Data Index: 1466661 (Python Code)

Max Activating Token Index: 628

Text #10

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.5146. Min Act: -0.0001

Data Index: 1517970 (Python Code)

Max Activating Token Index: 469

Text #11

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.5314. Min Act: -0.0001

Data Index: 1450017 (Python Code)

Max Activating Token Index: 442

Text #12

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.5475. Min Act: -0.0001

Data Index: 1574927 (Python Code)

Max Activating Token Index: 800

Text #13

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.0812. Min Act: -0.0001

Data Index: 1555555 (Python Code)

Max Activating Token Index: 264

Text #14

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.3391. Min Act: -0.0001

Data Index: 1375942 (Python Code)

Max Activating Token Index: 902

Text #15

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.7960. Min Act: -0.0001

Data Index: 1554972 (Python Code)

Max Activating Token Index: 276

Text #16

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.3455. Min Act: -0.0001

Data Index: 1602182 (Python Code)

Max Activating Token Index: 327

Text #17

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.4631. Min Act: -0.0001

Data Index: 1567971 (Python Code)

Max Activating Token Index: 556

Text #18

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.2997. Min Act: -0.0001

Data Index: 1595349 (Python Code)

Max Activating Token Index: 735

Text #19

Max Range: 3.9610. Min Range: -3.9610

Max Act: 3.6931. Min Act: -0.0001

Data Index: 1498727 (Python Code)

Max Activating Token Index: 447