Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1573 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.0724. Min Range: -1.0724
Max Act: 1.0724. Min Act: -0.0001
Data Index: 422246 (The Pile)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0724. Min Range: -1.0724
Max Act: 0.9813. Min Act: -0.0001
Data Index: 1417149 (The Pile)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0724. Min Range: -1.0724
Max Act: 1.0061. Min Act: -0.0001
Data Index: 908268 (The Pile)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0724. Min Range: -1.0724
Max Act: 1.0106. Min Act: -0.0001
Data Index: 581311 (The Pile)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0724. Min Range: -1.0724
Max Act: 0.9590. Min Act: -0.0001
Data Index: 224865 (The Pile)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0724. Min Range: -1.0724
Max Act: 0.9930. Min Act: -0.0001
Data Index: 227601 (The Pile)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0724. Min Range: -1.0724
Max Act: 0.9160. Min Act: -0.0001
Data Index: 936534 (The Pile)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0724. Min Range: -1.0724
Max Act: 0.9149. Min Act: -0.0001
Data Index: 414119 (The Pile)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0724. Min Range: -1.0724
Max Act: 0.9279. Min Act: -0.0001
Data Index: 1601927 (The Pile)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0724. Min Range: -1.0724
Max Act: 0.9864. Min Act: -0.0001
Data Index: 711137 (The Pile)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0724. Min Range: -1.0724
Max Act: 0.9210. Min Act: -0.0001
Data Index: 1478091 (The Pile)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0724. Min Range: -1.0724
Max Act: 0.9180. Min Act: -0.0001
Data Index: 1650435 (The Pile)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0724. Min Range: -1.0724
Max Act: 0.9200. Min Act: -0.0001
Data Index: 216478 (The Pile)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0724. Min Range: -1.0724
Max Act: 0.9407. Min Act: -0.0001
Data Index: 243115 (The Pile)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0724. Min Range: -1.0724
Max Act: 0.8791. Min Act: -0.0001
Data Index: 1026951 (The Pile)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0724. Min Range: -1.0724
Max Act: 0.9335. Min Act: -0.0001
Data Index: 1444304 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0724. Min Range: -1.0724
Max Act: 0.9248. Min Act: -0.0001
Data Index: 290007 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0724. Min Range: -1.0724
Max Act: 0.9248. Min Act: -0.0001
Data Index: 1314735 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0724. Min Range: -1.0724
Max Act: 0.9564. Min Act: -0.0001
Data Index: 1358045 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0724. Min Range: -1.0724
Max Act: 0.9230. Min Act: -0.0001
Data Index: 1648324 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19