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

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

Neuron 4890 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2577. Min Range: -1.2577

Max Act: 1.2577. Min Act: -0.0000

Data Index: 1078040 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 1.2577. Min Range: -1.2577

Max Act: 1.0823. Min Act: -0.0000

Data Index: 871993 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1044593 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.9095. Min Act: -0.0000

Data Index: 769212 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.8977. Min Act: -0.0000

Data Index: 85578 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.8633. Min Act: -0.0000

Data Index: 102366 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1270862 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.6832. Min Act: -0.0000

Data Index: 206722 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7972. Min Act: -0.0000

Data Index: 1023877 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.8125. Min Act: -0.0000

Data Index: 968585 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7678. Min Act: -0.0000

Data Index: 535260 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7857. Min Act: -0.0000

Data Index: 1201922 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7523. Min Act: -0.0000

Data Index: 1083637 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7607. Min Act: -0.0000

Data Index: 552503 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7320. Min Act: -0.0000

Data Index: 711405 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7337. Min Act: -0.0000

Data Index: 510330 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7078. Min Act: -0.0000

Data Index: 62653 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7203. Min Act: -0.0000

Data Index: 1003271 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.6996. Min Act: -0.0000

Data Index: 705443 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 1.2577. Min Range: -1.2577

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1164559 (C4 (Web Text))

Max Activating Token Index: 510