Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2418 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.2003. Min Range: -1.2003
Max Act: 1.1264. Min Act: -0.0001
Data Index: 1258359 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2003. Min Range: -1.2003
Max Act: 1.1633. Min Act: -0.0001
Data Index: 1256843 (The Pile)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2003. Min Range: -1.2003
Max Act: 1.0927. Min Act: -0.0001
Data Index: 701791 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2003. Min Range: -1.2003
Max Act: 1.2003. Min Act: -0.0001
Data Index: 1581286 (The Pile)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2003. Min Range: -1.2003
Max Act: 1.0172. Min Act: -0.0001
Data Index: 728004 (The Pile)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2003. Min Range: -1.2003
Max Act: 1.0373. Min Act: -0.0001
Data Index: 1086987 (The Pile)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2003. Min Range: -1.2003
Max Act: 0.9225. Min Act: -0.0001
Data Index: 660853 (The Pile)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2003. Min Range: -1.2003
Max Act: 0.9788. Min Act: -0.0001
Data Index: 1109550 (The Pile)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2003. Min Range: -1.2003
Max Act: 1.0011. Min Act: -0.0001
Data Index: 1197597 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2003. Min Range: -1.2003
Max Act: 0.9629. Min Act: -0.0001
Data Index: 413705 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2003. Min Range: -1.2003
Max Act: 0.9441. Min Act: -0.0001
Data Index: 422806 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2003. Min Range: -1.2003
Max Act: 0.9696. Min Act: -0.0001
Data Index: 1130256 (The Pile)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2003. Min Range: -1.2003
Max Act: 0.9667. Min Act: -0.0001
Data Index: 661816 (The Pile)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2003. Min Range: -1.2003
Max Act: 1.0176. Min Act: -0.0001
Data Index: 697879 (The Pile)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2003. Min Range: -1.2003
Max Act: 1.0859. Min Act: -0.0001
Data Index: 5200 (The Pile)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2003. Min Range: -1.2003
Max Act: 1.0119. Min Act: -0.0001
Data Index: 551591 (The Pile)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2003. Min Range: -1.2003
Max Act: 1.1027. Min Act: -0.0001
Data Index: 1074083 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2003. Min Range: -1.2003
Max Act: 1.1396. Min Act: -0.0001
Data Index: 417152 (The Pile)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2003. Min Range: -1.2003
Max Act: 1.0403. Min Act: -0.0001
Data Index: 779195 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2003. Min Range: -1.2003
Max Act: 1.0518. Min Act: -0.0001
Data Index: 643124 (The Pile)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19