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

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

Neuron 3676 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: 0.8751. Min Range: -0.8751

Max Act: 0.8751. Min Act: -0.0000

Data Index: 692769 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.7249. Min Act: -0.0000

Data Index: 747598 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.7525. Min Act: -0.0000

Data Index: 794209 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6543. Min Act: -0.0000

Data Index: 81505 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6450. Min Act: -0.0000

Data Index: 555137 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6340. Min Act: -0.0000

Data Index: 1200393 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6034. Min Act: -0.0000

Data Index: 907124 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6200. Min Act: -0.0000

Data Index: 412696 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1336093 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.5975. Min Act: -0.0000

Data Index: 703000 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.5857. Min Act: -0.0000

Data Index: 485877 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.5976. Min Act: -0.0000

Data Index: 866289 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1057341 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.5943. Min Act: -0.0000

Data Index: 22741 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6071. Min Act: -0.0000

Data Index: 399587 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6010. Min Act: -0.0000

Data Index: 110296 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.5992. Min Act: -0.0000

Data Index: 947510 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6311. Min Act: -0.0000

Data Index: 685620 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.6264. Min Act: -0.0000

Data Index: 371238 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.8751. Min Range: -0.8751

Max Act: 0.5663. Min Act: -0.0000

Data Index: 1126588 (C4 (Web Text))

Max Activating Token Index: 460