Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3044 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.6272. Min Act: -0.0000
Data Index: 746533 (The Pile)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.6029. Min Act: -0.0000
Data Index: 1557846 (The Pile)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.4827. Min Act: -0.0000
Data Index: 89385 (The Pile)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.5655. Min Act: -0.0000
Data Index: 843819 (The Pile)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.3588. Min Act: -0.0000
Data Index: 539966 (The Pile)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.4853. Min Act: -0.0000
Data Index: 1034133 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.3946. Min Act: -0.0000
Data Index: 1140527 (The Pile)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.4980. Min Act: -0.0000
Data Index: 930341 (The Pile)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.2149. Min Act: -0.0000
Data Index: 1395580 (The Pile)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.4380. Min Act: -0.0000
Data Index: 889935 (The Pile)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.4359. Min Act: -0.0000
Data Index: 616559 (The Pile)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.3255. Min Act: -0.0000
Data Index: 370885 (The Pile)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.3057. Min Act: -0.0000
Data Index: 218090 (The Pile)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.2591. Min Act: -0.0000
Data Index: 578647 (The Pile)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.3662. Min Act: -0.0000
Data Index: 227419 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.2778. Min Act: -0.0000
Data Index: 967662 (The Pile)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.2665. Min Act: -0.0000
Data Index: 1717924 (The Pile)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.1193. Min Act: -0.0000
Data Index: 173 (The Pile)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.1853. Min Act: -0.0000
Data Index: 1347545 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6272. Min Range: -1.6272
Max Act: 1.2487. Min Act: -0.0000
Data Index: 1887601 (The Pile)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19