Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1138 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0610. Min Act: 0.0000
Data Index: 1825571 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0573. Min Act: 0.0000
Data Index: 996161 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0563. Min Act: -0.0000
Data Index: 528416 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0560. Min Act: -0.0000
Data Index: 382049 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0542. Min Act: 0.0000
Data Index: 845315 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0534. Min Act: -0.0000
Data Index: 1126312 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0534. Min Act: -0.0000
Data Index: 601954 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0534. Min Act: -0.0000
Data Index: 1417283 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0534. Min Act: -0.0000
Data Index: 696237 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0534. Min Act: -0.0000
Data Index: 147021 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0534. Min Act: -0.0000
Data Index: 333697 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0534. Min Act: -0.0000
Data Index: 108764 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0534. Min Act: -0.0000
Data Index: 903410 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0534. Min Act: -0.0000
Data Index: 301987 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0534. Min Act: 0.0000
Data Index: 133130 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0534. Min Act: -0.0000
Data Index: 790055 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0534. Min Act: -0.0000
Data Index: 165192 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0534. Min Act: 0.0000
Data Index: 3698 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0534. Min Act: -0.0000
Data Index: 154103 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0610. Min Range: -0.0610
Max Act: 0.0534. Min Act: -0.0000
Data Index: 75254 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19