Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1886 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.5282. Min Range: -2.5282
Max Act: 2.5282. Min Act: -0.0001
Data Index: 220086 (The Pile)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5282. Min Range: -2.5282
Max Act: 2.0323. Min Act: -0.0001
Data Index: 49374 (The Pile)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5282. Min Range: -2.5282
Max Act: 2.2162. Min Act: -0.0001
Data Index: 1837224 (The Pile)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5282. Min Range: -2.5282
Max Act: 1.9027. Min Act: -0.0001
Data Index: 1417081 (The Pile)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5282. Min Range: -2.5282
Max Act: 1.9175. Min Act: -0.0001
Data Index: 732939 (The Pile)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5282. Min Range: -2.5282
Max Act: 2.0286. Min Act: -0.0001
Data Index: 1940571 (The Pile)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5282. Min Range: -2.5282
Max Act: 2.0715. Min Act: -0.0001
Data Index: 750997 (The Pile)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5282. Min Range: -2.5282
Max Act: 1.9174. Min Act: -0.0001
Data Index: 29081 (The Pile)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5282. Min Range: -2.5282
Max Act: 2.0182. Min Act: -0.0001
Data Index: 23451 (The Pile)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5282. Min Range: -2.5282
Max Act: 2.0149. Min Act: -0.0001
Data Index: 914292 (The Pile)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5282. Min Range: -2.5282
Max Act: 1.7138. Min Act: -0.0001
Data Index: 1631593 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5282. Min Range: -2.5282
Max Act: 1.8099. Min Act: -0.0001
Data Index: 1273079 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5282. Min Range: -2.5282
Max Act: 1.9100. Min Act: -0.0001
Data Index: 1796555 (The Pile)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5282. Min Range: -2.5282
Max Act: 1.9049. Min Act: -0.0001
Data Index: 1632623 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5282. Min Range: -2.5282
Max Act: 1.8159. Min Act: -0.0001
Data Index: 878080 (The Pile)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5282. Min Range: -2.5282
Max Act: 1.8403. Min Act: -0.0001
Data Index: 1315645 (The Pile)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5282. Min Range: -2.5282
Max Act: 2.1375. Min Act: -0.0001
Data Index: 1450117 (The Pile)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5282. Min Range: -2.5282
Max Act: 1.7485. Min Act: -0.0001
Data Index: 992606 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5282. Min Range: -2.5282
Max Act: 1.8377. Min Act: -0.0001
Data Index: 1715087 (The Pile)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5282. Min Range: -2.5282
Max Act: 1.6963. Min Act: -0.0001
Data Index: 265795 (The Pile)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19