Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2133 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5615. Min Act: -0.0001
Data Index: 1417499 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5692. Min Act: -0.0001
Data Index: 159867 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5692. Min Act: -0.0001
Data Index: 1122480 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5692. Min Act: -0.0001
Data Index: 1404433 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5692. Min Act: -0.0001
Data Index: 438286 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5692. Min Act: -0.0001
Data Index: 862815 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5692. Min Act: -0.0000
Data Index: 873557 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5692. Min Act: -0.0001
Data Index: 82912 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5692. Min Act: -0.0001
Data Index: 1285846 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5692. Min Act: -0.0001
Data Index: 178617 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5692. Min Act: -0.0001
Data Index: 1447972 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5692. Min Act: -0.0001
Data Index: 1030370 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5692. Min Act: -0.0000
Data Index: 302245 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5421. Min Act: -0.0000
Data Index: 1018801 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5421. Min Act: -0.0001
Data Index: 1415488 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5421. Min Act: -0.0001
Data Index: 420511 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5421. Min Act: -0.0000
Data Index: 807539 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5331. Min Act: -0.0001
Data Index: 474819 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5130. Min Act: -0.0001
Data Index: 1038753 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5692. Min Range: -0.5692
Max Act: 0.5308. Min Act: -0.0000
Data Index: 746465 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19