Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2551 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.8356. Min Act: -0.0000
Data Index: 1582458 (The Pile)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.5654. Min Act: -0.0000
Data Index: 1669575 (The Pile)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.8260. Min Act: 0.0000
Data Index: 1519621 (The Pile)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.7899. Min Act: -0.0000
Data Index: 1376752 (The Pile)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.5990. Min Act: -0.0000
Data Index: 1928959 (The Pile)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.4779. Min Act: -0.0000
Data Index: 881733 (The Pile)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0841. Min Range: -3.0841
Max Act: 3.0841. Min Act: -0.0000
Data Index: 1483203 (The Pile)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.7184. Min Act: -0.0000
Data Index: 1760503 (The Pile)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.2489. Min Act: -0.0000
Data Index: 751430 (The Pile)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.4935. Min Act: -0.0000
Data Index: 1259728 (The Pile)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.4474. Min Act: 0.0000
Data Index: 416670 (The Pile)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.7156. Min Act: -0.0000
Data Index: 378995 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.2711. Min Act: -0.0000
Data Index: 1547533 (The Pile)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.3588. Min Act: -0.0000
Data Index: 110118 (The Pile)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.2430. Min Act: 0.0000
Data Index: 774050 (The Pile)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.2554. Min Act: -0.0000
Data Index: 1659619 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.1079. Min Act: -0.0000
Data Index: 628234 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.0862. Min Act: -0.0000
Data Index: 1531067 (The Pile)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0841. Min Range: -3.0841
Max Act: 1.9165. Min Act: -0.0000
Data Index: 730761 (The Pile)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0841. Min Range: -3.0841
Max Act: 2.0111. Min Act: 0.0000
Data Index: 599837 (The Pile)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19