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

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

Neuron 2880 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.4633. Min Act: -0.0001

Data Index: 1467629 (Python Code)

Max Activating Token Index: 208

Text #1

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.4618. Min Act: -0.0001

Data Index: 1532692 (Python Code)

Max Activating Token Index: 312

Text #2

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.4808. Min Act: -0.0001

Data Index: 1447654 (Python Code)

Max Activating Token Index: 752

Text #3

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.4078. Min Act: -0.0001

Data Index: 1636857 (Python Code)

Max Activating Token Index: 106

Text #4

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3930. Min Act: -0.0001

Data Index: 1403696 (Python Code)

Max Activating Token Index: 363

Text #5

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3854. Min Act: -0.0001

Data Index: 1611030 (Python Code)

Max Activating Token Index: 376

Text #6

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3584. Min Act: -0.0001

Data Index: 1620536 (Python Code)

Max Activating Token Index: 600

Text #7

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3781. Min Act: -0.0001

Data Index: 1597696 (Python Code)

Max Activating Token Index: 80

Text #8

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3619. Min Act: -0.0001

Data Index: 1584204 (Python Code)

Max Activating Token Index: 887

Text #9

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3870. Min Act: -0.0001

Data Index: 1507178 (Python Code)

Max Activating Token Index: 224

Text #10

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3746. Min Act: -0.0001

Data Index: 1564098 (Python Code)

Max Activating Token Index: 363

Text #11

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3819. Min Act: -0.0001

Data Index: 1469071 (Python Code)

Max Activating Token Index: 337

Text #12

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3557. Min Act: -0.0001

Data Index: 1654508 (Python Code)

Max Activating Token Index: 531

Text #13

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1591678 (Python Code)

Max Activating Token Index: 310

Text #14

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3809. Min Act: -0.0001

Data Index: 1570543 (Python Code)

Max Activating Token Index: 377

Text #15

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3791. Min Act: -0.0001

Data Index: 1517320 (Python Code)

Max Activating Token Index: 453

Text #16

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.4038. Min Act: -0.0001

Data Index: 1582683 (Python Code)

Max Activating Token Index: 158

Text #17

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3802. Min Act: -0.0001

Data Index: 1397523 (Python Code)

Max Activating Token Index: 140

Text #18

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3686. Min Act: -0.0001

Data Index: 1404960 (Python Code)

Max Activating Token Index: 156

Text #19

Max Range: 0.4808. Min Range: -0.4808

Max Act: 0.3790. Min Act: -0.0001

Data Index: 1544214 (Python Code)

Max Activating Token Index: 942