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

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

Neuron 5761 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0626. Min Act: -0.0001

Data Index: 863106 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1180536 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0381. Min Act: -0.0001

Data Index: 1509480 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1434126 (Python Code)

Max Activating Token Index: 189

Text #4

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0334. Min Act: -0.0001

Data Index: 1389805 (Python Code)

Max Activating Token Index: 1002

Text #5

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0346. Min Act: -0.0001

Data Index: 546612 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0335. Min Act: -0.0001

Data Index: 980164 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1220726 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1497098 (Python Code)

Max Activating Token Index: 244

Text #9

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0336. Min Act: -0.0001

Data Index: 453092 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0333. Min Act: -0.0001

Data Index: 285011 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0324. Min Act: -0.0001

Data Index: 649544 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1420168 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0338. Min Act: -0.0001

Data Index: 1484359 (Python Code)

Max Activating Token Index: 666

Text #14

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0316. Min Act: -0.0001

Data Index: 1240908 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0329. Min Act: -0.0001

Data Index: 318760 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0309. Min Act: -0.0001

Data Index: 580811 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0320. Min Act: -0.0001

Data Index: 228090 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0304. Min Act: -0.0001

Data Index: 903945 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.0626. Min Range: -0.0626

Max Act: 0.0290. Min Act: -0.0001

Data Index: 79906 (C4 (Web Text))

Max Activating Token Index: 254