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

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

Neuron 580 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.2541. Min Act: -0.0001

Data Index: 1604582 (Python Code)

Max Activating Token Index: 564

Text #1

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.2139. Min Act: -0.0001

Data Index: 644555 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.0785. Min Act: -0.0001

Data Index: 81404 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.0442. Min Act: -0.0001

Data Index: 1537871 (Python Code)

Max Activating Token Index: 878

Text #4

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.0116. Min Act: -0.0001

Data Index: 1620124 (Python Code)

Max Activating Token Index: 1012

Text #5

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.0881. Min Act: -0.0001

Data Index: 1554383 (Python Code)

Max Activating Token Index: 1007

Text #6

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.0530. Min Act: -0.0001

Data Index: 1439579 (Python Code)

Max Activating Token Index: 499

Text #7

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.0113. Min Act: -0.0001

Data Index: 1511696 (Python Code)

Max Activating Token Index: 24

Text #8

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.8385. Min Act: -0.0001

Data Index: 1617567 (Python Code)

Max Activating Token Index: 715

Text #9

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9416. Min Act: -0.0001

Data Index: 1280198 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9943. Min Act: -0.0001

Data Index: 1591754 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.0277. Min Act: -0.0001

Data Index: 1557804 (Python Code)

Max Activating Token Index: 65

Text #12

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9689. Min Act: -0.0001

Data Index: 1456867 (Python Code)

Max Activating Token Index: 474

Text #13

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9931. Min Act: -0.0001

Data Index: 1453254 (Python Code)

Max Activating Token Index: 563

Text #14

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9897. Min Act: -0.0001

Data Index: 1374702 (Python Code)

Max Activating Token Index: 483

Text #15

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9617. Min Act: -0.0001

Data Index: 1581684 (Python Code)

Max Activating Token Index: 736

Text #16

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.8406. Min Act: -0.0001

Data Index: 1567130 (Python Code)

Max Activating Token Index: 843

Text #17

Max Range: 1.2541. Min Range: -1.2541

Max Act: 1.0057. Min Act: -0.0001

Data Index: 1105612 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9449. Min Act: -0.0001

Data Index: 1363529 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 1.2541. Min Range: -1.2541

Max Act: 0.9659. Min Act: -0.0001

Data Index: 311224 (C4 (Web Text))

Max Activating Token Index: 396