Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2321 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.1256. Min Range: -2.1256
Max Act: 2.1256. Min Act: -0.0000
Data Index: 1140566 (The Pile)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1256. Min Range: -2.1256
Max Act: 2.0774. Min Act: -0.0000
Data Index: 509627 (The Pile)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1256. Min Range: -2.1256
Max Act: 2.0219. Min Act: -0.0000
Data Index: 1931041 (The Pile)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1256. Min Range: -2.1256
Max Act: 1.9039. Min Act: -0.0000
Data Index: 537190 (The Pile)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1256. Min Range: -2.1256
Max Act: 1.9206. Min Act: -0.0000
Data Index: 717893 (The Pile)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1256. Min Range: -2.1256
Max Act: 1.8376. Min Act: -0.0000
Data Index: 319575 (The Pile)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1256. Min Range: -2.1256
Max Act: 2.0412. Min Act: -0.0000
Data Index: 1757672 (The Pile)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1256. Min Range: -2.1256
Max Act: 1.7703. Min Act: -0.0000
Data Index: 333717 (The Pile)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1256. Min Range: -2.1256
Max Act: 1.7864. Min Act: -0.0000
Data Index: 1884573 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1256. Min Range: -2.1256
Max Act: 1.8549. Min Act: -0.0000
Data Index: 1605144 (The Pile)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1256. Min Range: -2.1256
Max Act: 1.7158. Min Act: -0.0000
Data Index: 11838 (The Pile)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1256. Min Range: -2.1256
Max Act: 1.5049. Min Act: -0.0000
Data Index: 236436 (The Pile)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1256. Min Range: -2.1256
Max Act: 1.7118. Min Act: -0.0000
Data Index: 1970628 (The Pile)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1256. Min Range: -2.1256
Max Act: 1.6974. Min Act: -0.0000
Data Index: 245725 (The Pile)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1256. Min Range: -2.1256
Max Act: 1.6124. Min Act: -0.0000
Data Index: 175733 (The Pile)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1256. Min Range: -2.1256
Max Act: 1.6814. Min Act: -0.0000
Data Index: 1461702 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1256. Min Range: -2.1256
Max Act: 1.7578. Min Act: -0.0000
Data Index: 1784504 (The Pile)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1256. Min Range: -2.1256
Max Act: 1.7366. Min Act: -0.0000
Data Index: 1651485 (The Pile)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1256. Min Range: -2.1256
Max Act: 1.5504. Min Act: -0.0000
Data Index: 273676 (The Pile)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1256. Min Range: -2.1256
Max Act: 1.6599. Min Act: -0.0000
Data Index: 47781 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19