Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 820 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0761. Min Act: -0.0001
Data Index: 34581 (The Pile)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0689. Min Act: -0.0001
Data Index: 1296323 (The Pile)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0683. Min Act: -0.0001
Data Index: 66760 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0689. Min Act: -0.0001
Data Index: 1344532 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0689. Min Act: -0.0001
Data Index: 1179758 (The Pile)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0516. Min Act: -0.0001
Data Index: 1468946 (The Pile)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0681. Min Act: -0.0001
Data Index: 1865329 (The Pile)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0670. Min Act: -0.0001
Data Index: 960041 (The Pile)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0719. Min Act: -0.0001
Data Index: 1090153 (The Pile)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0717. Min Act: -0.0001
Data Index: 1253145 (The Pile)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0610. Min Act: -0.0001
Data Index: 689256 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0569. Min Act: -0.0001
Data Index: 817100 (The Pile)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0640. Min Act: -0.0001
Data Index: 1324659 (The Pile)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0640. Min Act: -0.0001
Data Index: 486797 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0566. Min Act: -0.0001
Data Index: 81864 (The Pile)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0652. Min Act: -0.0001
Data Index: 365750 (The Pile)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0603. Min Act: -0.0001
Data Index: 1770945 (The Pile)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0531. Min Act: -0.0001
Data Index: 1024750 (The Pile)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0545. Min Act: -0.0001
Data Index: 554781 (The Pile)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0761. Min Range: -0.0761
Max Act: 0.0602. Min Act: -0.0001
Data Index: 24856 (The Pile)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19