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

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

Neuron 4090 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8059. Min Act: -0.0001

Data Index: 343512 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8648. Min Act: -0.0000

Data Index: 12239 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8278. Min Act: -0.0001

Data Index: 1129362 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7751. Min Act: -0.0001

Data Index: 324988 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7888. Min Act: -0.0001

Data Index: 1096916 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7853. Min Act: -0.0001

Data Index: 1070448 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7534. Min Act: -0.0001

Data Index: 1224305 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7401. Min Act: -0.0001

Data Index: 1222876 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7209. Min Act: -0.0001

Data Index: 482074 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7852. Min Act: -0.0000

Data Index: 245293 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7445. Min Act: -0.0000

Data Index: 290928 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7339. Min Act: -0.0001

Data Index: 885792 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7787. Min Act: -0.0001

Data Index: 1046124 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7609. Min Act: -0.0000

Data Index: 419593 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6735. Min Act: -0.0000

Data Index: 866759 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7127. Min Act: -0.0001

Data Index: 645652 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6846. Min Act: -0.0001

Data Index: 1249323 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7190. Min Act: -0.0001

Data Index: 152240 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6601. Min Act: -0.0001

Data Index: 438056 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6902. Min Act: -0.0001

Data Index: 1347423 (C4 (Web Text))

Max Activating Token Index: 298