Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3591 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.8501. Min Act: -0.0001
Data Index: 1103161 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.1417. Min Act: -0.0001
Data Index: 599600 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8501. Min Range: -2.8501
Max Act: 1.9353. Min Act: -0.0001
Data Index: 27630 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8501. Min Range: -2.8501
Max Act: 1.8797. Min Act: -0.0001
Data Index: 300830 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8501. Min Range: -2.8501
Max Act: 1.8704. Min Act: -0.0001
Data Index: 1212837 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.0118. Min Act: -0.0001
Data Index: 204812 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8501. Min Range: -2.8501
Max Act: 2.0752. Min Act: -0.0001
Data Index: 1031607 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8501. Min Range: -2.8501
Max Act: 1.8713. Min Act: -0.0001
Data Index: 629089 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8501. Min Range: -2.8501
Max Act: 1.9596. Min Act: -0.0001
Data Index: 1084304 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8501. Min Range: -2.8501
Max Act: 1.9040. Min Act: -0.0001
Data Index: 952007 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8501. Min Range: -2.8501
Max Act: 1.8458. Min Act: -0.0001
Data Index: 1088453 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8501. Min Range: -2.8501
Max Act: 1.4614. Min Act: -0.0001
Data Index: 1076680 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8501. Min Range: -2.8501
Max Act: 1.9258. Min Act: -0.0001
Data Index: 623748 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8501. Min Range: -2.8501
Max Act: 1.7915. Min Act: -0.0001
Data Index: 820766 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8501. Min Range: -2.8501
Max Act: 1.7443. Min Act: -0.0001
Data Index: 648797 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8501. Min Range: -2.8501
Max Act: 1.9599. Min Act: -0.0001
Data Index: 1342510 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8501. Min Range: -2.8501
Max Act: 1.9655. Min Act: -0.0001
Data Index: 392085 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8501. Min Range: -2.8501
Max Act: 1.5429. Min Act: -0.0001
Data Index: 517790 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8501. Min Range: -2.8501
Max Act: 1.6119. Min Act: -0.0001
Data Index: 355553 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8501. Min Range: -2.8501
Max Act: 1.6663. Min Act: -0.0001
Data Index: 721945 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19