Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4075 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.9513. Min Range: -4.9513
Max Act: 4.7732. Min Act: -0.0001
Data Index: 276480 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9513. Min Range: -4.9513
Max Act: 4.9513. Min Act: -0.0001
Data Index: 418685 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9513. Min Range: -4.9513
Max Act: 4.7548. Min Act: -0.0001
Data Index: 48097 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9513. Min Range: -4.9513
Max Act: 4.0363. Min Act: -0.0001
Data Index: 75995 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9513. Min Range: -4.9513
Max Act: 4.5018. Min Act: -0.0001
Data Index: 488835 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9513. Min Range: -4.9513
Max Act: 4.0124. Min Act: -0.0001
Data Index: 602097 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9513. Min Range: -4.9513
Max Act: 4.1463. Min Act: -0.0001
Data Index: 1072577 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9513. Min Range: -4.9513
Max Act: 3.7879. Min Act: -0.0001
Data Index: 1290947 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9513. Min Range: -4.9513
Max Act: 3.7673. Min Act: -0.0001
Data Index: 1345189 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9513. Min Range: -4.9513
Max Act: 4.1497. Min Act: -0.0001
Data Index: 201792 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9513. Min Range: -4.9513
Max Act: 4.1376. Min Act: -0.0001
Data Index: 93073 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9513. Min Range: -4.9513
Max Act: 3.3289. Min Act: -0.0001
Data Index: 453277 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9513. Min Range: -4.9513
Max Act: 3.8065. Min Act: -0.0001
Data Index: 303842 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9513. Min Range: -4.9513
Max Act: 3.6242. Min Act: -0.0001
Data Index: 190287 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9513. Min Range: -4.9513
Max Act: 3.5629. Min Act: -0.0001
Data Index: 1122226 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9513. Min Range: -4.9513
Max Act: 3.9906. Min Act: -0.0001
Data Index: 1016011 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9513. Min Range: -4.9513
Max Act: 3.9623. Min Act: -0.0001
Data Index: 1253898 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9513. Min Range: -4.9513
Max Act: 3.5144. Min Act: -0.0001
Data Index: 638011 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9513. Min Range: -4.9513
Max Act: 4.1205. Min Act: -0.0001
Data Index: 204925 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9513. Min Range: -4.9513
Max Act: 3.7372. Min Act: -0.0001
Data Index: 859219 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19