Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3288 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5881. Min Act: -0.0001

Data Index: 1129015 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4737. Min Act: -0.0001

Data Index: 767367 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4885. Min Act: -0.0001

Data Index: 498279 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5243. Min Act: -0.0001

Data Index: 1577946 (Python Code)

Max Activating Token Index: 132

Text #4

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5298. Min Act: -0.0001

Data Index: 788782 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5083. Min Act: -0.0001

Data Index: 1246069 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5220. Min Act: -0.0001

Data Index: 275405 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4882. Min Act: -0.0001

Data Index: 772106 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4892. Min Act: -0.0001

Data Index: 853072 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4770. Min Act: -0.0001

Data Index: 258743 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4811. Min Act: -0.0001

Data Index: 1539668 (Python Code)

Max Activating Token Index: 907

Text #11

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4795. Min Act: -0.0001

Data Index: 325370 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.5311. Min Act: -0.0001

Data Index: 527463 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4445. Min Act: -0.0001

Data Index: 1063836 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4071. Min Act: -0.0001

Data Index: 466471 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4478. Min Act: -0.0001

Data Index: 1131270 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.3954. Min Act: -0.0001

Data Index: 222688 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.4065. Min Act: -0.0001

Data Index: 1085274 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.3894. Min Act: -0.0001

Data Index: 344308 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.5881. Min Range: -0.5881

Max Act: 0.3985. Min Act: -0.0001

Data Index: 516506 (C4 (Web Text))

Max Activating Token Index: 685