Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 679 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.4583. Min Act: -0.0000
Data Index: 798848 (The Pile)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.4157. Min Act: -0.0001
Data Index: 1229961 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.3890. Min Act: -0.0000
Data Index: 1607744 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.4283. Min Act: -0.0001
Data Index: 194192 (The Pile)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.3821. Min Act: -0.0001
Data Index: 574800 (The Pile)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.3599. Min Act: -0.0001
Data Index: 52102 (The Pile)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.3610. Min Act: -0.0000
Data Index: 714106 (The Pile)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.3687. Min Act: -0.0001
Data Index: 1120387 (The Pile)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.3795. Min Act: -0.0001
Data Index: 582817 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.3576. Min Act: -0.0001
Data Index: 1171907 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.3771. Min Act: -0.0001
Data Index: 1834820 (The Pile)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.3485. Min Act: -0.0001
Data Index: 784256 (The Pile)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.3475. Min Act: -0.0001
Data Index: 548495 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.3559. Min Act: -0.0001
Data Index: 1377792 (The Pile)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.3316. Min Act: -0.0001
Data Index: 655371 (The Pile)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.3397. Min Act: -0.0001
Data Index: 955052 (The Pile)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.3216. Min Act: -0.0001
Data Index: 1360695 (The Pile)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.3269. Min Act: -0.0001
Data Index: 1055113 (The Pile)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.3282. Min Act: -0.0000
Data Index: 701860 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4583. Min Range: -0.4583
Max Act: 0.3379. Min Act: -0.0001
Data Index: 298318 (The Pile)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19