Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 111 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 23703 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 13300 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 27250 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 30500 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 11569 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 160 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 25586 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 10740 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 28047 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 1434 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 15477 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 4571 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 414 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 22557 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 22294 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 4341 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 19255 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 4346 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 17918 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0622. Min Range: -0.0622
Max Act: 0.0622. Min Act: -0.0002
Data Index: 15945 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19