Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3977 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0002
Data Index: 1976770 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0002
Data Index: 1454675 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0002
Data Index: 1359223 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0002
Data Index: 1147821 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0002
Data Index: 1004662 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0002
Data Index: 884118 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0002
Data Index: 827896 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0003
Data Index: 813528 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0002
Data Index: 60228 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0002
Data Index: 679896 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0002
Data Index: 1691557 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0002
Data Index: 1619471 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0002
Data Index: 1613287 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0002
Data Index: 1547975 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0002
Data Index: 1488455 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0002
Data Index: 384215 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0002
Data Index: 1469192 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0546. Min Act: -0.0002
Data Index: 123912 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0502. Min Act: -0.0002
Data Index: 1283842 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0546. Min Range: -0.0546
Max Act: 0.0502. Min Act: -0.0002
Data Index: 1426888 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19