Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 14 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.7692. Min Act: -0.0001
Data Index: 855099 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.7438. Min Act: -0.0001
Data Index: 448755 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.6214. Min Act: -0.0001
Data Index: 142117 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.5724. Min Act: -0.0001
Data Index: 652184 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.5840. Min Act: -0.0001
Data Index: 505503 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.5464. Min Act: -0.0001
Data Index: 434912 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.5681. Min Act: -0.0001
Data Index: 59223 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.4980. Min Act: -0.0001
Data Index: 671240 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.5728. Min Act: -0.0001
Data Index: 126466 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.5344. Min Act: -0.0001
Data Index: 1743046 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.4961. Min Act: -0.0001
Data Index: 826930 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.4778. Min Act: -0.0001
Data Index: 797979 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.4778. Min Act: -0.0001
Data Index: 1954214 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.4778. Min Act: -0.0001
Data Index: 1566050 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.4553. Min Act: -0.0001
Data Index: 1123173 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.5229. Min Act: -0.0001
Data Index: 571075 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.4844. Min Act: -0.0001
Data Index: 917733 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.4728. Min Act: -0.0001
Data Index: 1458179 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.4697. Min Act: -0.0001
Data Index: 1965800 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7692. Min Range: -0.7692
Max Act: 0.5024. Min Act: -0.0001
Data Index: 281045 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19