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

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

Neuron 2100 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.5295. Min Act: -0.0000

Data Index: 1477299 (Python Code)

Max Activating Token Index: 463

Text #1

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.2111. Min Act: -0.0000

Data Index: 1422737 (Python Code)

Max Activating Token Index: 143

Text #2

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.1494. Min Act: -0.0000

Data Index: 452685 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.0903. Min Act: -0.0000

Data Index: 838516 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.1013. Min Act: -0.0000

Data Index: 1532323 (Python Code)

Max Activating Token Index: 633

Text #5

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.0605. Min Act: -0.0000

Data Index: 1518301 (Python Code)

Max Activating Token Index: 525

Text #6

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.0099. Min Act: -0.0000

Data Index: 1415873 (Python Code)

Max Activating Token Index: 624

Text #7

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.0711. Min Act: -0.0000

Data Index: 1528023 (Python Code)

Max Activating Token Index: 268

Text #8

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.1309. Min Act: -0.0000

Data Index: 1069019 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 1.5295. Min Range: -1.5295

Max Act: 0.9811. Min Act: -0.0000

Data Index: 1587012 (Python Code)

Max Activating Token Index: 632

Text #10

Max Range: 1.5295. Min Range: -1.5295

Max Act: 1.0987. Min Act: -0.0000

Data Index: 1240302 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 1.5295. Min Range: -1.5295

Max Act: 0.9316. Min Act: -0.0000

Data Index: 1386800 (Python Code)

Max Activating Token Index: 54

Text #12

Max Range: 1.5295. Min Range: -1.5295

Max Act: 0.9221. Min Act: -0.0000

Data Index: 1368197 (Python Code)

Max Activating Token Index: 67

Text #13

Max Range: 1.5295. Min Range: -1.5295

Max Act: 0.9791. Min Act: -0.0000

Data Index: 15179 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 1.5295. Min Range: -1.5295

Max Act: 0.8192. Min Act: -0.0000

Data Index: 1400823 (Python Code)

Max Activating Token Index: 825

Text #15

Max Range: 1.5295. Min Range: -1.5295

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1286725 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 1.5295. Min Range: -1.5295

Max Act: 0.8425. Min Act: -0.0000

Data Index: 1643067 (Python Code)

Max Activating Token Index: 240

Text #17

Max Range: 1.5295. Min Range: -1.5295

Max Act: 0.8708. Min Act: -0.0000

Data Index: 1338593 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 1.5295. Min Range: -1.5295

Max Act: 0.8265. Min Act: -0.0000

Data Index: 632203 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 1.5295. Min Range: -1.5295

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1087577 (C4 (Web Text))

Max Activating Token Index: 323