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

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

Neuron 568 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.4046. Min Act: -0.0000

Data Index: 1500478 (Python Code)

Max Activating Token Index: 927

Text #1

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.1614. Min Act: -0.0000

Data Index: 1102943 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.0238. Min Act: -0.0000

Data Index: 543162 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 3.4046. Min Range: -3.4046

Max Act: 2.6456. Min Act: -0.0000

Data Index: 1371904 (Python Code)

Max Activating Token Index: 465

Text #4

Max Range: 3.4046. Min Range: -3.4046

Max Act: 2.7388. Min Act: -0.0000

Data Index: 1463830 (Python Code)

Max Activating Token Index: 737

Text #5

Max Range: 3.4046. Min Range: -3.4046

Max Act: 2.7376. Min Act: -0.0000

Data Index: 885308 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 3.4046. Min Range: -3.4046

Max Act: 2.5632. Min Act: -0.0000

Data Index: 108482 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 3.4046. Min Range: -3.4046

Max Act: 2.3851. Min Act: -0.0000

Data Index: 505239 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 3.4046. Min Range: -3.4046

Max Act: 2.0751. Min Act: -0.0000

Data Index: 516222 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 3.4046. Min Range: -3.4046

Max Act: 2.3051. Min Act: -0.0000

Data Index: 1069926 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 3.4046. Min Range: -3.4046

Max Act: 2.2691. Min Act: -0.0000

Data Index: 90819 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 3.4046. Min Range: -3.4046

Max Act: 2.2249. Min Act: -0.0000

Data Index: 1347263 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 3.4046. Min Range: -3.4046

Max Act: 2.2189. Min Act: -0.0000

Data Index: 1220249 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 3.4046. Min Range: -3.4046

Max Act: 2.3356. Min Act: -0.0000

Data Index: 956693 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 3.4046. Min Range: -3.4046

Max Act: 2.0588. Min Act: -0.0000

Data Index: 230109 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 3.4046. Min Range: -3.4046

Max Act: 2.2861. Min Act: -0.0000

Data Index: 684630 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 3.4046. Min Range: -3.4046

Max Act: 2.0847. Min Act: -0.0000

Data Index: 937046 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 3.4046. Min Range: -3.4046

Max Act: 2.1718. Min Act: -0.0000

Data Index: 90307 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 3.4046. Min Range: -3.4046

Max Act: 2.0589. Min Act: -0.0000

Data Index: 4737 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 3.4046. Min Range: -3.4046

Max Act: 2.1535. Min Act: -0.0000

Data Index: 929705 (C4 (Web Text))

Max Activating Token Index: 185