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

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

Neuron 4869 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4743. Min Range: -4.4743

Max Act: 4.1090. Min Act: -0.0000

Data Index: 1435877 (Python Code)

Max Activating Token Index: 651

Text #1

Max Range: 4.4743. Min Range: -4.4743

Max Act: 4.4743. Min Act: -0.0000

Data Index: 1366847 (Python Code)

Max Activating Token Index: 37

Text #2

Max Range: 4.4743. Min Range: -4.4743

Max Act: 4.1954. Min Act: -0.0000

Data Index: 1568528 (Python Code)

Max Activating Token Index: 50

Text #3

Max Range: 4.4743. Min Range: -4.4743

Max Act: 3.9678. Min Act: -0.0000

Data Index: 1633111 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 4.4743. Min Range: -4.4743

Max Act: 3.9577. Min Act: -0.0000

Data Index: 1476475 (Python Code)

Max Activating Token Index: 554

Text #5

Max Range: 4.4743. Min Range: -4.4743

Max Act: 3.8896. Min Act: -0.0000

Data Index: 1625427 (Python Code)

Max Activating Token Index: 431

Text #6

Max Range: 4.4743. Min Range: -4.4743

Max Act: 3.8853. Min Act: -0.0000

Data Index: 1458273 (Python Code)

Max Activating Token Index: 74

Text #7

Max Range: 4.4743. Min Range: -4.4743

Max Act: 3.8065. Min Act: -0.0000

Data Index: 1517299 (Python Code)

Max Activating Token Index: 105

Text #8

Max Range: 4.4743. Min Range: -4.4743

Max Act: 3.9628. Min Act: -0.0000

Data Index: 1611721 (Python Code)

Max Activating Token Index: 33

Text #9

Max Range: 4.4743. Min Range: -4.4743

Max Act: 3.7898. Min Act: -0.0000

Data Index: 1567295 (Python Code)

Max Activating Token Index: 575

Text #10

Max Range: 4.4743. Min Range: -4.4743

Max Act: 3.7562. Min Act: -0.0000

Data Index: 1512218 (Python Code)

Max Activating Token Index: 89

Text #11

Max Range: 4.4743. Min Range: -4.4743

Max Act: 3.6277. Min Act: -0.0000

Data Index: 1590430 (Python Code)

Max Activating Token Index: 196

Text #12

Max Range: 4.4743. Min Range: -4.4743

Max Act: 3.7663. Min Act: -0.0000

Data Index: 1486667 (Python Code)

Max Activating Token Index: 523

Text #13

Max Range: 4.4743. Min Range: -4.4743

Max Act: 3.5841. Min Act: -0.0000

Data Index: 1477416 (Python Code)

Max Activating Token Index: 284

Text #14

Max Range: 4.4743. Min Range: -4.4743

Max Act: 3.7076. Min Act: -0.0000

Data Index: 1572949 (Python Code)

Max Activating Token Index: 563

Text #15

Max Range: 4.4743. Min Range: -4.4743

Max Act: 3.5415. Min Act: -0.0000

Data Index: 1523064 (Python Code)

Max Activating Token Index: 162

Text #16

Max Range: 4.4743. Min Range: -4.4743

Max Act: 3.6864. Min Act: -0.0000

Data Index: 1655694 (Python Code)

Max Activating Token Index: 26

Text #17

Max Range: 4.4743. Min Range: -4.4743

Max Act: 3.6248. Min Act: -0.0000

Data Index: 1414142 (Python Code)

Max Activating Token Index: 503

Text #18

Max Range: 4.4743. Min Range: -4.4743

Max Act: 3.5957. Min Act: -0.0000

Data Index: 1424403 (Python Code)

Max Activating Token Index: 562

Text #19

Max Range: 4.4743. Min Range: -4.4743

Max Act: 3.7466. Min Act: -0.0000

Data Index: 1578577 (Python Code)

Max Activating Token Index: 364