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

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

Neuron 1404 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2735. Min Range: -1.2735

Max Act: 1.2735. Min Act: -0.0000

Data Index: 1502601 (Python Code)

Max Activating Token Index: 686

Text #1

Max Range: 1.2735. Min Range: -1.2735

Max Act: 1.0685. Min Act: -0.0000

Data Index: 1564823 (Python Code)

Max Activating Token Index: 178

Text #2

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.8860. Min Act: -0.0000

Data Index: 1620582 (Python Code)

Max Activating Token Index: 441

Text #3

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1518681 (Python Code)

Max Activating Token Index: 859

Text #4

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.8823. Min Act: -0.0000

Data Index: 1555286 (Python Code)

Max Activating Token Index: 693

Text #5

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.7795. Min Act: -0.0000

Data Index: 968130 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1565130 (Python Code)

Max Activating Token Index: 271

Text #7

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1368535 (Python Code)

Max Activating Token Index: 773

Text #8

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.7423. Min Act: -0.0000

Data Index: 848910 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1598602 (Python Code)

Max Activating Token Index: 116

Text #10

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1555060 (Python Code)

Max Activating Token Index: 344

Text #11

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.7982. Min Act: 0.0000

Data Index: 1393813 (Python Code)

Max Activating Token Index: 80

Text #12

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.7278. Min Act: -0.0000

Data Index: 229719 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.7280. Min Act: -0.0000

Data Index: 953164 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.7127. Min Act: -0.0000

Data Index: 612564 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.7674. Min Act: -0.0000

Data Index: 733065 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.7632. Min Act: -0.0000

Data Index: 1378261 (Python Code)

Max Activating Token Index: 58

Text #17

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.7550. Min Act: -0.0000

Data Index: 1062599 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1573247 (Python Code)

Max Activating Token Index: 184

Text #19

Max Range: 1.2735. Min Range: -1.2735

Max Act: 0.6712. Min Act: 0.0000

Data Index: 1387589 (Python Code)

Max Activating Token Index: 262