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

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

Neuron 4051 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1612018 (Python Code)

Max Activating Token Index: 244

Text #1

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1642367 (Python Code)

Max Activating Token Index: 209

Text #2

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.7000. Min Act: -0.0000

Data Index: 991747 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1541680 (Python Code)

Max Activating Token Index: 263

Text #4

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6547. Min Act: -0.0000

Data Index: 1441805 (Python Code)

Max Activating Token Index: 85

Text #5

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6848. Min Act: 0.0000

Data Index: 1601208 (Python Code)

Max Activating Token Index: 138

Text #6

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6052. Min Act: -0.0000

Data Index: 868936 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1453619 (Python Code)

Max Activating Token Index: 687

Text #8

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.5969. Min Act: -0.0000

Data Index: 1525571 (Python Code)

Max Activating Token Index: 578

Text #9

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1396366 (Python Code)

Max Activating Token Index: 541

Text #10

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1600156 (Python Code)

Max Activating Token Index: 635

Text #11

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.5876. Min Act: -0.0000

Data Index: 1639763 (Python Code)

Max Activating Token Index: 325

Text #12

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1374623 (Python Code)

Max Activating Token Index: 964

Text #13

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.5419. Min Act: -0.0000

Data Index: 452925 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6003. Min Act: -0.0000

Data Index: 1436078 (Python Code)

Max Activating Token Index: 107

Text #15

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1565694 (Python Code)

Max Activating Token Index: 176

Text #16

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.5889. Min Act: -0.0000

Data Index: 555233 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1584093 (Python Code)

Max Activating Token Index: 931

Text #18

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.6087. Min Act: -0.0000

Data Index: 1485443 (Python Code)

Max Activating Token Index: 675

Text #19

Max Range: 0.7978. Min Range: -0.7978

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1465650 (Python Code)

Max Activating Token Index: 750