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

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

Neuron 6017 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.8788. Min Act: -0.0001

Data Index: 372251 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7846. Min Act: -0.0000

Data Index: 106713 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.6704. Min Act: -0.0001

Data Index: 608787 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.6325. Min Act: -0.0001

Data Index: 400571 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.5667. Min Act: -0.0001

Data Index: 503819 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.6141. Min Act: -0.0000

Data Index: 440860 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.6096. Min Act: -0.0001

Data Index: 321360 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1256796 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.5867. Min Act: -0.0001

Data Index: 366686 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.6210. Min Act: -0.0000

Data Index: 508834 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.5426. Min Act: -0.0000

Data Index: 369955 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.5747. Min Act: -0.0001

Data Index: 445328 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.5257. Min Act: -0.0001

Data Index: 1297946 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.5309. Min Act: -0.0000

Data Index: 1151594 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.4940. Min Act: -0.0001

Data Index: 674989 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.5372. Min Act: -0.0000

Data Index: 21896 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.5353. Min Act: -0.0000

Data Index: 970140 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.5600. Min Act: -0.0001

Data Index: 898643 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.4595. Min Act: -0.0001

Data Index: 847676 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1002860 (C4 (Web Text))

Max Activating Token Index: 45