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

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

Neuron 4835 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2727. Min Range: -2.2727

Max Act: 2.2727. Min Act: -0.0000

Data Index: 1451528 (Python Code)

Max Activating Token Index: 469

Text #1

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.9908. Min Act: -0.0000

Data Index: 1391628 (Python Code)

Max Activating Token Index: 189

Text #2

Max Range: 2.2727. Min Range: -2.2727

Max Act: 2.0379. Min Act: -0.0000

Data Index: 1442176 (Python Code)

Max Activating Token Index: 587

Text #3

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.8065. Min Act: -0.0000

Data Index: 1574289 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.8624. Min Act: -0.0000

Data Index: 1463643 (Python Code)

Max Activating Token Index: 887

Text #5

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.8857. Min Act: -0.0000

Data Index: 1607407 (Python Code)

Max Activating Token Index: 595

Text #6

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.8939. Min Act: -0.0000

Data Index: 1571336 (Python Code)

Max Activating Token Index: 710

Text #7

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.7862. Min Act: -0.0000

Data Index: 1556833 (Python Code)

Max Activating Token Index: 314

Text #8

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.7769. Min Act: -0.0000

Data Index: 1494228 (Python Code)

Max Activating Token Index: 1009

Text #9

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.8569. Min Act: -0.0000

Data Index: 1438455 (Python Code)

Max Activating Token Index: 425

Text #10

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.7449. Min Act: -0.0000

Data Index: 1449921 (Python Code)

Max Activating Token Index: 432

Text #11

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.7775. Min Act: 0.0000

Data Index: 1506379 (Python Code)

Max Activating Token Index: 232

Text #12

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.7605. Min Act: -0.0000

Data Index: 1423260 (Python Code)

Max Activating Token Index: 692

Text #13

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.6756. Min Act: -0.0000

Data Index: 1651735 (Python Code)

Max Activating Token Index: 497

Text #14

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.6359. Min Act: -0.0000

Data Index: 1583459 (Python Code)

Max Activating Token Index: 826

Text #15

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.6520. Min Act: -0.0000

Data Index: 1617578 (Python Code)

Max Activating Token Index: 30

Text #16

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.5954. Min Act: -0.0000

Data Index: 1399650 (Python Code)

Max Activating Token Index: 203

Text #17

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.5745. Min Act: 0.0000

Data Index: 1447335 (Python Code)

Max Activating Token Index: 108

Text #18

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.6108. Min Act: -0.0000

Data Index: 1408733 (Python Code)

Max Activating Token Index: 1016

Text #19

Max Range: 2.2727. Min Range: -2.2727

Max Act: 1.5620. Min Act: -0.0000

Data Index: 1635342 (Python Code)

Max Activating Token Index: 365