Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2955 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.8589. Min Act: -0.0001
Data Index: 435803 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.6506. Min Act: -0.0001
Data Index: 187051 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.6948. Min Act: -0.0001
Data Index: 388398 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.8129. Min Act: -0.0001
Data Index: 24469 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.7373. Min Act: -0.0001
Data Index: 245912 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.7411. Min Act: -0.0001
Data Index: 706312 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.6559. Min Act: -0.0002
Data Index: 99825 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.6576. Min Act: -0.0001
Data Index: 476708 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.7140. Min Act: -0.0001
Data Index: 1121144 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.6109. Min Act: -0.0001
Data Index: 1125779 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.6360. Min Act: -0.0001
Data Index: 1244842 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.6389. Min Act: -0.0001
Data Index: 353582 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.5025. Min Act: -0.0001
Data Index: 737714 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.6350. Min Act: -0.0001
Data Index: 390675 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.5703. Min Act: -0.0001
Data Index: 294105 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.5335. Min Act: -0.0001
Data Index: 27843 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.5712. Min Act: -0.0002
Data Index: 242095 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.5245. Min Act: -0.0001
Data Index: 201084 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.5781. Min Act: -0.0001
Data Index: 1128241 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8589. Min Range: -1.8589
Max Act: 1.5846. Min Act: -0.0001
Data Index: 1303566 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19