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

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

Neuron 181 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.9525. Min Act: -0.0003

Data Index: 1552911 (Python Code)

Max Activating Token Index: 113

Text #1

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8847. Min Act: -0.0003

Data Index: 1459485 (Python Code)

Max Activating Token Index: 371

Text #2

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8815. Min Act: -0.0003

Data Index: 1498405 (Python Code)

Max Activating Token Index: 503

Text #3

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.9118. Min Act: -0.0003

Data Index: 1375660 (Python Code)

Max Activating Token Index: 96

Text #4

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.9753. Min Act: -0.0003

Data Index: 1417769 (Python Code)

Max Activating Token Index: 371

Text #5

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.9091. Min Act: -0.0003

Data Index: 1496946 (Python Code)

Max Activating Token Index: 918

Text #6

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.9547. Min Act: -0.0003

Data Index: 1548852 (Python Code)

Max Activating Token Index: 321

Text #7

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8807. Min Act: -0.0003

Data Index: 1383653 (Python Code)

Max Activating Token Index: 372

Text #8

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8631. Min Act: -0.0003

Data Index: 1619958 (Python Code)

Max Activating Token Index: 719

Text #9

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8345. Min Act: -0.0003

Data Index: 1654165 (Python Code)

Max Activating Token Index: 188

Text #10

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8291. Min Act: -0.0003

Data Index: 1457319 (Python Code)

Max Activating Token Index: 654

Text #11

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8345. Min Act: -0.0003

Data Index: 1628667 (Python Code)

Max Activating Token Index: 319

Text #12

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.7792. Min Act: -0.0003

Data Index: 1582418 (Python Code)

Max Activating Token Index: 137

Text #13

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8397. Min Act: -0.0003

Data Index: 1554234 (Python Code)

Max Activating Token Index: 17

Text #14

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8337. Min Act: -0.0003

Data Index: 1533911 (Python Code)

Max Activating Token Index: 250

Text #15

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8295. Min Act: -0.0003

Data Index: 1404137 (Python Code)

Max Activating Token Index: 813

Text #16

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.7818. Min Act: -0.0003

Data Index: 1368168 (Python Code)

Max Activating Token Index: 77

Text #17

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8056. Min Act: -0.0003

Data Index: 1653318 (Python Code)

Max Activating Token Index: 240

Text #18

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.7770. Min Act: -0.0003

Data Index: 1651934 (Python Code)

Max Activating Token Index: 207

Text #19

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.7750. Min Act: -0.0003

Data Index: 1608030 (Python Code)

Max Activating Token Index: 371