Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3420 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.4487. Min Act: -0.0000
Data Index: 43460 (The Pile)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.2564. Min Act: -0.0000
Data Index: 21241 (The Pile)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.2046. Min Act: -0.0000
Data Index: 185528 (The Pile)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.2309. Min Act: -0.0000
Data Index: 214401 (The Pile)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.1991. Min Act: -0.0000
Data Index: 492454 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.1914. Min Act: -0.0000
Data Index: 187456 (The Pile)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.1497. Min Act: -0.0000
Data Index: 130565 (The Pile)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.3302. Min Act: -0.0000
Data Index: 104381 (The Pile)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.0964. Min Act: -0.0000
Data Index: 970088 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.0976. Min Act: -0.0000
Data Index: 721327 (The Pile)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.1311. Min Act: -0.0000
Data Index: 171838 (The Pile)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.2161. Min Act: -0.0000
Data Index: 1757358 (The Pile)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.0971. Min Act: -0.0000
Data Index: 1109916 (The Pile)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4487. Min Range: -1.4487
Max Act: 0.9561. Min Act: -0.0000
Data Index: 685140 (The Pile)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.0129. Min Act: -0.0000
Data Index: 1681631 (The Pile)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.0370. Min Act: -0.0000
Data Index: 117376 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.0931. Min Act: -0.0000
Data Index: 909468 (The Pile)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.0913. Min Act: -0.0000
Data Index: 1202544 (The Pile)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.0548. Min Act: -0.0000
Data Index: 737069 (The Pile)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4487. Min Range: -1.4487
Max Act: 1.0478. Min Act: -0.0000
Data Index: 1246403 (The Pile)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19