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

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

Neuron 4412 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.5562. Min Range: -5.5562

Max Act: 5.5562. Min Act: -0.0000

Data Index: 520243 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 5.5562. Min Range: -5.5562

Max Act: 4.1865. Min Act: -0.0000

Data Index: 642662 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 5.5562. Min Range: -5.5562

Max Act: 3.8951. Min Act: -0.0000

Data Index: 564358 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 5.5562. Min Range: -5.5562

Max Act: 3.8118. Min Act: -0.0000

Data Index: 1541029 (Python Code)

Max Activating Token Index: 187

Text #4

Max Range: 5.5562. Min Range: -5.5562

Max Act: 3.4028. Min Act: -0.0000

Data Index: 938744 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 5.5562. Min Range: -5.5562

Max Act: 3.4894. Min Act: -0.0000

Data Index: 319563 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 5.5562. Min Range: -5.5562

Max Act: 3.5502. Min Act: -0.0000

Data Index: 1488737 (Python Code)

Max Activating Token Index: 174

Text #7

Max Range: 5.5562. Min Range: -5.5562

Max Act: 3.1670. Min Act: -0.0000

Data Index: 1387 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 5.5562. Min Range: -5.5562

Max Act: 3.3817. Min Act: -0.0000

Data Index: 1625043 (Python Code)

Max Activating Token Index: 260

Text #9

Max Range: 5.5562. Min Range: -5.5562

Max Act: 3.2012. Min Act: -0.0000

Data Index: 1656430 (Python Code)

Max Activating Token Index: 306

Text #10

Max Range: 5.5562. Min Range: -5.5562

Max Act: 3.0624. Min Act: -0.0000

Data Index: 1386651 (Python Code)

Max Activating Token Index: 227

Text #11

Max Range: 5.5562. Min Range: -5.5562

Max Act: 3.1871. Min Act: -0.0000

Data Index: 1374665 (Python Code)

Max Activating Token Index: 133

Text #12

Max Range: 5.5562. Min Range: -5.5562

Max Act: 2.9801. Min Act: -0.0000

Data Index: 1087071 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 5.5562. Min Range: -5.5562

Max Act: 3.1083. Min Act: -0.0000

Data Index: 1628325 (Python Code)

Max Activating Token Index: 152

Text #14

Max Range: 5.5562. Min Range: -5.5562

Max Act: 2.9934. Min Act: -0.0000

Data Index: 1368282 (Python Code)

Max Activating Token Index: 306

Text #15

Max Range: 5.5562. Min Range: -5.5562

Max Act: 3.1127. Min Act: -0.0000

Data Index: 1501270 (Python Code)

Max Activating Token Index: 325

Text #16

Max Range: 5.5562. Min Range: -5.5562

Max Act: 2.9635. Min Act: -0.0000

Data Index: 1446977 (Python Code)

Max Activating Token Index: 185

Text #17

Max Range: 5.5562. Min Range: -5.5562

Max Act: 2.9132. Min Act: -0.0000

Data Index: 1480897 (Python Code)

Max Activating Token Index: 265

Text #18

Max Range: 5.5562. Min Range: -5.5562

Max Act: 3.0005. Min Act: -0.0000

Data Index: 1503944 (Python Code)

Max Activating Token Index: 270

Text #19

Max Range: 5.5562. Min Range: -5.5562

Max Act: 3.1308. Min Act: -0.0000

Data Index: 1615161 (Python Code)

Max Activating Token Index: 221