Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3480 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.3855. Min Act: -0.0001
Data Index: 567573 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.4509. Min Act: -0.0001
Data Index: 1906913 (The Pile)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.7393. Min Act: -0.0001
Data Index: 1802629 (The Pile)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.3863. Min Act: -0.0001
Data Index: 230156 (The Pile)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.3054. Min Act: -0.0001
Data Index: 344283 (The Pile)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.2302. Min Act: -0.0001
Data Index: 121903 (The Pile)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.2517. Min Act: -0.0001
Data Index: 640707 (The Pile)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.3845. Min Act: -0.0001
Data Index: 543304 (The Pile)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.3665. Min Act: -0.0001
Data Index: 64832 (The Pile)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.1987. Min Act: -0.0001
Data Index: 13635 (The Pile)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.2217. Min Act: -0.0001
Data Index: 523694 (The Pile)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.4638. Min Act: -0.0001
Data Index: 1466585 (The Pile)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.0050. Min Act: -0.0001
Data Index: 1818907 (The Pile)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.3253. Min Act: -0.0001
Data Index: 413391 (The Pile)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.3863. Min Act: -0.0001
Data Index: 1491647 (The Pile)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.4575. Min Act: -0.0001
Data Index: 1107062 (The Pile)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.3602. Min Act: -0.0001
Data Index: 39365 (The Pile)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.3751. Min Act: -0.0001
Data Index: 831749 (The Pile)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.1084. Min Act: -0.0001
Data Index: 584881 (The Pile)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7393. Min Range: -1.7393
Max Act: 1.2956. Min Act: -0.0001
Data Index: 1443287 (The Pile)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19