Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3685 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2112. Min Range: -1.2112

Max Act: 1.2112. Min Act: -0.0000

Data Index: 1260336 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 1.2112. Min Range: -1.2112

Max Act: 1.1671. Min Act: -0.0000

Data Index: 999319 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 1.2112. Min Range: -1.2112

Max Act: 1.1516. Min Act: -0.0000

Data Index: 831523 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 1.2112. Min Range: -1.2112

Max Act: 1.0790. Min Act: -0.0000

Data Index: 946452 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.9858. Min Act: -0.0000

Data Index: 676011 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.9247. Min Act: -0.0000

Data Index: 839489 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.9411. Min Act: -0.0000

Data Index: 880226 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.9584. Min Act: -0.0000

Data Index: 311248 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.9855. Min Act: -0.0000

Data Index: 1168497 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 1.2112. Min Range: -1.2112

Max Act: 1.0099. Min Act: -0.0000

Data Index: 819917 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.9858. Min Act: -0.0000

Data Index: 195579 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.9837. Min Act: -0.0000

Data Index: 123929 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.8571. Min Act: -0.0000

Data Index: 225235 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.9116. Min Act: -0.0000

Data Index: 168693 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.9541. Min Act: -0.0000

Data Index: 142113 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.8421. Min Act: -0.0000

Data Index: 916248 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.8977. Min Act: -0.0000

Data Index: 18444 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.8867. Min Act: -0.0000

Data Index: 720414 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1287196 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.8793. Min Act: -0.0000

Data Index: 1347245 (C4 (Web Text))

Max Activating Token Index: 846