Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 465 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.6156. Min Range: -2.6156
Max Act: 2.6156. Min Act: -0.0001
Data Index: 1116433 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6156. Min Range: -2.6156
Max Act: 2.2857. Min Act: -0.0001
Data Index: 1337869 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6156. Min Range: -2.6156
Max Act: 2.2526. Min Act: -0.0001
Data Index: 131388 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6156. Min Range: -2.6156
Max Act: 2.3602. Min Act: -0.0001
Data Index: 145837 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6156. Min Range: -2.6156
Max Act: 2.0347. Min Act: -0.0001
Data Index: 613844 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6156. Min Range: -2.6156
Max Act: 2.0549. Min Act: -0.0001
Data Index: 345020 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6156. Min Range: -2.6156
Max Act: 1.9801. Min Act: -0.0001
Data Index: 703779 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6156. Min Range: -2.6156
Max Act: 1.8860. Min Act: -0.0001
Data Index: 1096854 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6156. Min Range: -2.6156
Max Act: 1.8958. Min Act: -0.0001
Data Index: 964879 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6156. Min Range: -2.6156
Max Act: 1.7909. Min Act: -0.0001
Data Index: 1326433 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6156. Min Range: -2.6156
Max Act: 1.8474. Min Act: -0.0001
Data Index: 1220245 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6156. Min Range: -2.6156
Max Act: 1.8485. Min Act: -0.0001
Data Index: 694805 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6156. Min Range: -2.6156
Max Act: 1.8239. Min Act: -0.0001
Data Index: 1264578 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6156. Min Range: -2.6156
Max Act: 1.6593. Min Act: -0.0001
Data Index: 278523 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6156. Min Range: -2.6156
Max Act: 1.8324. Min Act: -0.0001
Data Index: 986520 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6156. Min Range: -2.6156
Max Act: 1.6439. Min Act: -0.0001
Data Index: 1552918 (Python Code)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6156. Min Range: -2.6156
Max Act: 1.8095. Min Act: -0.0001
Data Index: 90674 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6156. Min Range: -2.6156
Max Act: 1.6089. Min Act: -0.0001
Data Index: 1500428 (Python Code)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6156. Min Range: -2.6156
Max Act: 1.3087. Min Act: -0.0001
Data Index: 1013336 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6156. Min Range: -2.6156
Max Act: 1.5508. Min Act: -0.0001
Data Index: 449321 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19