Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 782 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 4.1268. Min Range: -4.1268
Max Act: 4.1268. Min Act: -0.0000
Data Index: 1093675 (The Pile)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.9439. Min Act: -0.0000
Data Index: 30001 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1268. Min Range: -4.1268
Max Act: 4.0276. Min Act: -0.0000
Data Index: 668238 (The Pile)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.4684. Min Act: -0.0000
Data Index: 62637 (The Pile)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.4690. Min Act: -0.0000
Data Index: 474893 (The Pile)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.6903. Min Act: -0.0000
Data Index: 122536 (The Pile)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.2708. Min Act: -0.0000
Data Index: 235419 (The Pile)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.4036. Min Act: -0.0000
Data Index: 1521968 (The Pile)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.6534. Min Act: -0.0000
Data Index: 558856 (The Pile)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.5083. Min Act: -0.0000
Data Index: 1720918 (The Pile)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.4154. Min Act: -0.0000
Data Index: 84321 (The Pile)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.4535. Min Act: -0.0000
Data Index: 363696 (The Pile)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.3966. Min Act: -0.0000
Data Index: 25990 (The Pile)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.6473. Min Act: -0.0000
Data Index: 1135230 (The Pile)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.4905. Min Act: -0.0000
Data Index: 1946342 (The Pile)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.2906. Min Act: -0.0000
Data Index: 556691 (The Pile)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.2681. Min Act: -0.0000
Data Index: 816857 (The Pile)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.2422. Min Act: -0.0000
Data Index: 341941 (The Pile)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.2055. Min Act: -0.0000
Data Index: 7657 (The Pile)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1268. Min Range: -4.1268
Max Act: 3.0589. Min Act: -0.0000
Data Index: 1381369 (The Pile)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19