Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1774 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.9873. Min Act: -0.0001
Data Index: 598362 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.9073. Min Act: -0.0001
Data Index: 1678037 (The Pile)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.9907. Min Act: -0.0001
Data Index: 1094135 (The Pile)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.9859. Min Act: -0.0001
Data Index: 1866714 (The Pile)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.8667. Min Act: -0.0001
Data Index: 42173 (The Pile)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.8931. Min Act: -0.0001
Data Index: 273485 (The Pile)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.9208. Min Act: -0.0001
Data Index: 1019966 (The Pile)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.8523. Min Act: -0.0001
Data Index: 1945409 (The Pile)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.8637. Min Act: -0.0001
Data Index: 684914 (The Pile)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.9216. Min Act: -0.0001
Data Index: 713550 (The Pile)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.8499. Min Act: -0.0001
Data Index: 343506 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.8312. Min Act: -0.0001
Data Index: 1677559 (The Pile)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.7509. Min Act: -0.0001
Data Index: 143726 (The Pile)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.8731. Min Act: -0.0001
Data Index: 1050234 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.7549. Min Act: -0.0001
Data Index: 689530 (The Pile)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.8842. Min Act: -0.0001
Data Index: 649155 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.7429. Min Act: -0.0000
Data Index: 780810 (The Pile)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.7772. Min Act: -0.0001
Data Index: 1649896 (The Pile)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.8062. Min Act: -0.0001
Data Index: 1079831 (The Pile)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9907. Min Range: -0.9907
Max Act: 0.7315. Min Act: -0.0001
Data Index: 76702 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19