Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3683 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.6620. Min Act: -0.0001
Data Index: 650250 (The Pile)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.6911. Min Act: -0.0001
Data Index: 1512076 (The Pile)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.5180. Min Act: -0.0001
Data Index: 1027223 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.4353. Min Act: -0.0001
Data Index: 1288580 (The Pile)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.5438. Min Act: -0.0001
Data Index: 1009010 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.5910. Min Act: -0.0001
Data Index: 605382 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.5752. Min Act: -0.0001
Data Index: 799216 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.4545. Min Act: -0.0001
Data Index: 1382926 (The Pile)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.5121. Min Act: -0.0001
Data Index: 715236 (The Pile)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.5605. Min Act: -0.0001
Data Index: 1929077 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.5321. Min Act: -0.0001
Data Index: 1168997 (The Pile)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.5229. Min Act: -0.0001
Data Index: 1369013 (The Pile)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.5057. Min Act: -0.0001
Data Index: 1997263 (The Pile)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.5587. Min Act: -0.0001
Data Index: 1953669 (The Pile)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.4529. Min Act: -0.0001
Data Index: 1255144 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.4529. Min Act: -0.0001
Data Index: 400242 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.4509. Min Act: -0.0001
Data Index: 1943464 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.4267. Min Act: -0.0001
Data Index: 1585689 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.4859. Min Act: -0.0001
Data Index: 1819986 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6911. Min Range: -1.6911
Max Act: 1.3588. Min Act: -0.0001
Data Index: 1899695 (The Pile)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19