Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3544 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0367. Min Act: -0.0000
Data Index: 1743848 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 712433 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 337617 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 823762 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 90035 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 247925 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 589082 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 355065 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 327718 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 114363 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 825699 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 3702 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 671368 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 706948 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 269350 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 5120 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 399508 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 149868 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 758207 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0367. Min Range: -0.0367
Max Act: 0.0350. Min Act: -0.0000
Data Index: 675026 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19