Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1072 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.7317. Min Act: -0.0000
Data Index: 1437775 (The Pile)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.6260. Min Act: -0.0001
Data Index: 468373 (The Pile)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.4621. Min Act: -0.0001
Data Index: 546232 (The Pile)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.7142. Min Act: -0.0001
Data Index: 1349424 (The Pile)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.4488. Min Act: -0.0001
Data Index: 431967 (The Pile)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.4139. Min Act: -0.0001
Data Index: 1942946 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.4414. Min Act: -0.0001
Data Index: 105855 (The Pile)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.4217. Min Act: -0.0001
Data Index: 1465741 (The Pile)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.4458. Min Act: -0.0001
Data Index: 143753 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.4646. Min Act: -0.0001
Data Index: 1650102 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.4168. Min Act: -0.0001
Data Index: 28631 (The Pile)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.3950. Min Act: -0.0001
Data Index: 1837800 (The Pile)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.2413. Min Act: -0.0001
Data Index: 1729235 (The Pile)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.3938. Min Act: -0.0001
Data Index: 1085404 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.2996. Min Act: -0.0001
Data Index: 1516983 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.3666. Min Act: -0.0001
Data Index: 1748877 (The Pile)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.3100. Min Act: -0.0001
Data Index: 843206 (The Pile)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.2845. Min Act: -0.0001
Data Index: 889566 (The Pile)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.3048. Min Act: -0.0001
Data Index: 1992889 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7317. Min Range: -1.7317
Max Act: 1.2410. Min Act: -0.0001
Data Index: 591916 (The Pile)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19