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

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

Neuron 1829 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.7072. Min Act: -0.0002

Data Index: 179602 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.2472. Min Act: -0.0002

Data Index: 240846 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.1852. Min Act: -0.0002

Data Index: 927461 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.1696. Min Act: -0.0002

Data Index: 1091503 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 2.7072. Min Range: -2.7072

Max Act: 2.0754. Min Act: -0.0003

Data Index: 995381 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.9665. Min Act: -0.0002

Data Index: 795896 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.9459. Min Act: -0.0002

Data Index: 1332353 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.9249. Min Act: -0.0002

Data Index: 992213 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.9906. Min Act: -0.0002

Data Index: 877495 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.9727. Min Act: -0.0002

Data Index: 968454 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.9705. Min Act: -0.0002

Data Index: 1114485 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.9637. Min Act: -0.0002

Data Index: 263947 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.8842. Min Act: -0.0002

Data Index: 900718 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.8849. Min Act: -0.0002

Data Index: 205854 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.8277. Min Act: -0.0002

Data Index: 1004185 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.8067. Min Act: -0.0002

Data Index: 1113806 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.8323. Min Act: -0.0002

Data Index: 1379616 (Python Code)

Max Activating Token Index: 390

Text #17

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.8325. Min Act: -0.0002

Data Index: 63140 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.8414. Min Act: -0.0002

Data Index: 804838 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 2.7072. Min Range: -2.7072

Max Act: 1.8433. Min Act: -0.0002

Data Index: 1116685 (C4 (Web Text))

Max Activating Token Index: 852