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

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

Neuron 4729 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7638. Min Range: -4.7638

Max Act: 4.7638. Min Act: -0.0000

Data Index: 1480365 (Python Code)

Max Activating Token Index: 736

Text #1

Max Range: 4.7638. Min Range: -4.7638

Max Act: 4.5622. Min Act: -0.0000

Data Index: 1429751 (Python Code)

Max Activating Token Index: 675

Text #2

Max Range: 4.7638. Min Range: -4.7638

Max Act: 4.4127. Min Act: -0.0000

Data Index: 1597077 (Python Code)

Max Activating Token Index: 265

Text #3

Max Range: 4.7638. Min Range: -4.7638

Max Act: 4.2192. Min Act: -0.0000

Data Index: 1370352 (Python Code)

Max Activating Token Index: 652

Text #4

Max Range: 4.7638. Min Range: -4.7638

Max Act: 4.3947. Min Act: -0.0000

Data Index: 1405920 (Python Code)

Max Activating Token Index: 250

Text #5

Max Range: 4.7638. Min Range: -4.7638

Max Act: 4.5654. Min Act: -0.0000

Data Index: 1599001 (Python Code)

Max Activating Token Index: 895

Text #6

Max Range: 4.7638. Min Range: -4.7638

Max Act: 4.1930. Min Act: -0.0000

Data Index: 1496318 (Python Code)

Max Activating Token Index: 782

Text #7

Max Range: 4.7638. Min Range: -4.7638

Max Act: 4.3702. Min Act: -0.0000

Data Index: 1633139 (Python Code)

Max Activating Token Index: 887

Text #8

Max Range: 4.7638. Min Range: -4.7638

Max Act: 4.3866. Min Act: -0.0000

Data Index: 1453188 (Python Code)

Max Activating Token Index: 258

Text #9

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.9617. Min Act: -0.0000

Data Index: 1439221 (Python Code)

Max Activating Token Index: 512

Text #10

Max Range: 4.7638. Min Range: -4.7638

Max Act: 4.1287. Min Act: -0.0000

Data Index: 1432877 (Python Code)

Max Activating Token Index: 834

Text #11

Max Range: 4.7638. Min Range: -4.7638

Max Act: 4.3002. Min Act: -0.0000

Data Index: 1396139 (Python Code)

Max Activating Token Index: 741

Text #12

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.6343. Min Act: -0.0000

Data Index: 1622753 (Python Code)

Max Activating Token Index: 272

Text #13

Max Range: 4.7638. Min Range: -4.7638

Max Act: 4.1040. Min Act: -0.0000

Data Index: 1456675 (Python Code)

Max Activating Token Index: 625

Text #14

Max Range: 4.7638. Min Range: -4.7638

Max Act: 4.0701. Min Act: -0.0000

Data Index: 1373641 (Python Code)

Max Activating Token Index: 511

Text #15

Max Range: 4.7638. Min Range: -4.7638

Max Act: 4.0558. Min Act: -0.0000

Data Index: 1194612 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 4.7638. Min Range: -4.7638

Max Act: 4.2233. Min Act: -0.0000

Data Index: 1407688 (Python Code)

Max Activating Token Index: 774

Text #17

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.8188. Min Act: -0.0000

Data Index: 1585317 (Python Code)

Max Activating Token Index: 192

Text #18

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.9705. Min Act: -0.0000

Data Index: 1380648 (Python Code)

Max Activating Token Index: 617

Text #19

Max Range: 4.7638. Min Range: -4.7638

Max Act: 3.8187. Min Act: -0.0000

Data Index: 1404184 (Python Code)

Max Activating Token Index: 144