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

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

Neuron 2390 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4361. Min Range: -2.4361

Max Act: 2.4361. Min Act: -0.0000

Data Index: 797436 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 2.4361. Min Range: -2.4361

Max Act: 1.3423. Min Act: -0.0000

Data Index: 1061818 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 2.4361. Min Range: -2.4361

Max Act: 1.0786. Min Act: -0.0000

Data Index: 933557 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 2.4361. Min Range: -2.4361

Max Act: 0.8776. Min Act: -0.0000

Data Index: 172785 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 2.4361. Min Range: -2.4361

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1134616 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 2.4361. Min Range: -2.4361

Max Act: 0.9063. Min Act: -0.0000

Data Index: 722962 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 2.4361. Min Range: -2.4361

Max Act: 0.7822. Min Act: -0.0000

Data Index: 30086 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 2.4361. Min Range: -2.4361

Max Act: 0.8353. Min Act: -0.0000

Data Index: 895198 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 2.4361. Min Range: -2.4361

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1223727 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 2.4361. Min Range: -2.4361

Max Act: 0.7771. Min Act: -0.0000

Data Index: 36034 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 2.4361. Min Range: -2.4361

Max Act: 0.8364. Min Act: -0.0000

Data Index: 953367 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 2.4361. Min Range: -2.4361

Max Act: 0.8107. Min Act: -0.0000

Data Index: 659567 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 2.4361. Min Range: -2.4361

Max Act: 0.7369. Min Act: -0.0000

Data Index: 644146 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 2.4361. Min Range: -2.4361

Max Act: 0.7273. Min Act: -0.0000

Data Index: 561350 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 2.4361. Min Range: -2.4361

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1291718 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 2.4361. Min Range: -2.4361

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1343405 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 2.4361. Min Range: -2.4361

Max Act: 0.7117. Min Act: -0.0000

Data Index: 988539 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 2.4361. Min Range: -2.4361

Max Act: 0.6231. Min Act: -0.0000

Data Index: 886203 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 2.4361. Min Range: -2.4361

Max Act: 0.6807. Min Act: -0.0000

Data Index: 367916 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 2.4361. Min Range: -2.4361

Max Act: 0.6484. Min Act: -0.0000

Data Index: 997950 (C4 (Web Text))

Max Activating Token Index: 633