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

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

Neuron 2437 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5638. Min Range: -2.5638

Max Act: 2.5447. Min Act: -0.0000

Data Index: 73365 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 2.5638. Min Range: -2.5638

Max Act: 2.5376. Min Act: -0.0000

Data Index: 1544744 (Python Code)

Max Activating Token Index: 191

Text #2

Max Range: 2.5638. Min Range: -2.5638

Max Act: 2.5638. Min Act: -0.0000

Data Index: 1447745 (Python Code)

Max Activating Token Index: 854

Text #3

Max Range: 2.5638. Min Range: -2.5638

Max Act: 2.3648. Min Act: -0.0000

Data Index: 1588692 (Python Code)

Max Activating Token Index: 372

Text #4

Max Range: 2.5638. Min Range: -2.5638

Max Act: 2.4015. Min Act: -0.0000

Data Index: 1387623 (Python Code)

Max Activating Token Index: 256

Text #5

Max Range: 2.5638. Min Range: -2.5638

Max Act: 2.2474. Min Act: -0.0000

Data Index: 1527697 (Python Code)

Max Activating Token Index: 822

Text #6

Max Range: 2.5638. Min Range: -2.5638

Max Act: 2.2261. Min Act: -0.0000

Data Index: 1595094 (Python Code)

Max Activating Token Index: 545

Text #7

Max Range: 2.5638. Min Range: -2.5638

Max Act: 2.1509. Min Act: -0.0000

Data Index: 1598459 (Python Code)

Max Activating Token Index: 675

Text #8

Max Range: 2.5638. Min Range: -2.5638

Max Act: 2.1424. Min Act: -0.0000

Data Index: 1628601 (Python Code)

Max Activating Token Index: 882

Text #9

Max Range: 2.5638. Min Range: -2.5638

Max Act: 2.1458. Min Act: -0.0000

Data Index: 1618794 (Python Code)

Max Activating Token Index: 74

Text #10

Max Range: 2.5638. Min Range: -2.5638

Max Act: 2.1306. Min Act: -0.0000

Data Index: 1418949 (Python Code)

Max Activating Token Index: 373

Text #11

Max Range: 2.5638. Min Range: -2.5638

Max Act: 2.0277. Min Act: -0.0000

Data Index: 841261 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 2.5638. Min Range: -2.5638

Max Act: 2.2012. Min Act: -0.0000

Data Index: 1383783 (Python Code)

Max Activating Token Index: 815

Text #13

Max Range: 2.5638. Min Range: -2.5638

Max Act: 2.0694. Min Act: -0.0000

Data Index: 1395765 (Python Code)

Max Activating Token Index: 628

Text #14

Max Range: 2.5638. Min Range: -2.5638

Max Act: 2.0577. Min Act: -0.0000

Data Index: 1633164 (Python Code)

Max Activating Token Index: 974

Text #15

Max Range: 2.5638. Min Range: -2.5638

Max Act: 1.9310. Min Act: -0.0000

Data Index: 1545875 (Python Code)

Max Activating Token Index: 809

Text #16

Max Range: 2.5638. Min Range: -2.5638

Max Act: 2.1593. Min Act: -0.0000

Data Index: 1575398 (Python Code)

Max Activating Token Index: 752

Text #17

Max Range: 2.5638. Min Range: -2.5638

Max Act: 2.0319. Min Act: -0.0000

Data Index: 1648581 (Python Code)

Max Activating Token Index: 316

Text #18

Max Range: 2.5638. Min Range: -2.5638

Max Act: 1.9961. Min Act: -0.0000

Data Index: 1425618 (Python Code)

Max Activating Token Index: 541

Text #19

Max Range: 2.5638. Min Range: -2.5638

Max Act: 1.9922. Min Act: -0.0000

Data Index: 1445951 (Python Code)

Max Activating Token Index: 181