Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2544 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.7544. Min Act: -0.0001
Data Index: 247227 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.7275. Min Act: -0.0001
Data Index: 327913 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.6693. Min Act: -0.0001
Data Index: 561784 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.7011. Min Act: -0.0001
Data Index: 1194401 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.7260. Min Act: -0.0001
Data Index: 1314842 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.6789. Min Act: -0.0001
Data Index: 57233 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.6629. Min Act: -0.0001
Data Index: 1248866 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.6607. Min Act: -0.0001
Data Index: 419966 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.5895. Min Act: -0.0001
Data Index: 707560 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.6747. Min Act: -0.0001
Data Index: 714712 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.6702. Min Act: -0.0001
Data Index: 115309 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.6308. Min Act: -0.0001
Data Index: 187135 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.6411. Min Act: -0.0001
Data Index: 586591 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.6343. Min Act: -0.0001
Data Index: 1185609 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.6393. Min Act: -0.0001
Data Index: 920487 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.6355. Min Act: -0.0001
Data Index: 1347554 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.6331. Min Act: -0.0001
Data Index: 617920 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.6478. Min Act: -0.0001
Data Index: 60740 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.6183. Min Act: -0.0001
Data Index: 1079919 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7544. Min Range: -0.7544
Max Act: 0.6339. Min Act: -0.0001
Data Index: 236757 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19