Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3848 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.7751. Min Act: -0.0000
Data Index: 1673376 (The Pile)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.5425. Min Act: -0.0000
Data Index: 1517527 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.5674. Min Act: -0.0000
Data Index: 1744662 (The Pile)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.4739. Min Act: -0.0000
Data Index: 984877 (The Pile)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.2330. Min Act: -0.0000
Data Index: 1872713 (The Pile)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.4400. Min Act: -0.0000
Data Index: 1744489 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.3155. Min Act: -0.0000
Data Index: 10971 (The Pile)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.4034. Min Act: -0.0000
Data Index: 1386591 (The Pile)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.3690. Min Act: -0.0000
Data Index: 96634 (The Pile)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.2260. Min Act: -0.0000
Data Index: 70885 (The Pile)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.2821. Min Act: -0.0000
Data Index: 1917721 (The Pile)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.2482. Min Act: -0.0000
Data Index: 685366 (The Pile)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.2429. Min Act: -0.0000
Data Index: 749908 (The Pile)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.4589. Min Act: -0.0000
Data Index: 1642853 (The Pile)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.4063. Min Act: -0.0000
Data Index: 625053 (The Pile)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.1782. Min Act: -0.0000
Data Index: 569583 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.3266. Min Act: -0.0000
Data Index: 1378099 (The Pile)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.1831. Min Act: -0.0000
Data Index: 288452 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.1880. Min Act: -0.0000
Data Index: 468504 (The Pile)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7751. Min Range: -1.7751
Max Act: 1.1872. Min Act: -0.0000
Data Index: 220264 (The Pile)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19