Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2471 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.6743. Min Act: -0.0000
Data Index: 1890701 (The Pile)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.5951. Min Act: -0.0000
Data Index: 1295645 (The Pile)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.5792. Min Act: -0.0001
Data Index: 359931 (The Pile)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.5535. Min Act: -0.0000
Data Index: 1808658 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.5847. Min Act: -0.0001
Data Index: 303055 (The Pile)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.5730. Min Act: -0.0001
Data Index: 1208481 (The Pile)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.5572. Min Act: 0.0000
Data Index: 1576414 (The Pile)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.5801. Min Act: -0.0000
Data Index: 376689 (The Pile)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.5543. Min Act: 0.0000
Data Index: 1825200 (The Pile)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.5501. Min Act: 0.0001
Data Index: 1996623 (The Pile)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.5227. Min Act: -0.0001
Data Index: 1586496 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.5149. Min Act: -0.0001
Data Index: 717845 (The Pile)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.5161. Min Act: -0.0001
Data Index: 474162 (The Pile)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.5267. Min Act: 0.0000
Data Index: 1288671 (The Pile)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.5098. Min Act: 0.0000
Data Index: 371023 (The Pile)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.5069. Min Act: -0.0001
Data Index: 957098 (The Pile)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.5056. Min Act: 0.0000
Data Index: 80114 (The Pile)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.4855. Min Act: -0.0001
Data Index: 111572 (The Pile)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.4821. Min Act: -0.0001
Data Index: 1326413 (The Pile)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6743. Min Range: -0.6743
Max Act: 0.5106. Min Act: -0.0001
Data Index: 1925957 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19