Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 886 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0016. Min Act: -0.0001
Data Index: 1329118 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0015. Min Act: -0.0001
Data Index: 494547 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0014. Min Act: -0.0001
Data Index: 118407 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0014. Min Act: -0.0001
Data Index: 585064 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0014. Min Act: -0.0001
Data Index: 501397 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0014. Min Act: -0.0001
Data Index: 1287977 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0013. Min Act: -0.0001
Data Index: 1681728 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0013. Min Act: -0.0001
Data Index: 1858324 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0013. Min Act: -0.0001
Data Index: 1849978 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0013. Min Act: -0.0001
Data Index: 810283 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0013. Min Act: -0.0001
Data Index: 1808221 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0012. Min Act: -0.0001
Data Index: 1755636 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0012. Min Act: -0.0001
Data Index: 143464 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0012. Min Act: -0.0001
Data Index: 1976975 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0012. Min Act: -0.0001
Data Index: 652528 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0012. Min Act: -0.0001
Data Index: 615589 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0012. Min Act: -0.0001
Data Index: 1725142 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0012. Min Act: -0.0001
Data Index: 619139 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0011. Min Act: -0.0001
Data Index: 22336 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0016. Min Range: -0.0016
Max Act: 0.0011. Min Act: -0.0001
Data Index: 700844 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19