Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3784 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.5502. Min Range: -2.5502
Max Act: 2.5502. Min Act: -0.0000
Data Index: 680768 (The Pile)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5502. Min Range: -2.5502
Max Act: 2.2738. Min Act: -0.0000
Data Index: 710764 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5502. Min Range: -2.5502
Max Act: 2.0136. Min Act: -0.0000
Data Index: 1694033 (The Pile)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5502. Min Range: -2.5502
Max Act: 1.8565. Min Act: -0.0000
Data Index: 733940 (The Pile)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5502. Min Range: -2.5502
Max Act: 1.7630. Min Act: -0.0000
Data Index: 238652 (The Pile)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5502. Min Range: -2.5502
Max Act: 1.8677. Min Act: -0.0000
Data Index: 1965065 (The Pile)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5502. Min Range: -2.5502
Max Act: 1.7860. Min Act: -0.0000
Data Index: 1957490 (The Pile)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5502. Min Range: -2.5502
Max Act: 1.5684. Min Act: -0.0000
Data Index: 1782207 (The Pile)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5502. Min Range: -2.5502
Max Act: 1.6124. Min Act: -0.0000
Data Index: 1302191 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5502. Min Range: -2.5502
Max Act: 1.6854. Min Act: -0.0000
Data Index: 485769 (The Pile)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5502. Min Range: -2.5502
Max Act: 1.6081. Min Act: -0.0000
Data Index: 1305404 (The Pile)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5502. Min Range: -2.5502
Max Act: 1.7029. Min Act: -0.0000
Data Index: 1920482 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5502. Min Range: -2.5502
Max Act: 1.4883. Min Act: -0.0000
Data Index: 577717 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5502. Min Range: -2.5502
Max Act: 1.5539. Min Act: -0.0000
Data Index: 1542935 (The Pile)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5502. Min Range: -2.5502
Max Act: 1.5004. Min Act: -0.0000
Data Index: 1252798 (The Pile)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5502. Min Range: -2.5502
Max Act: 1.5381. Min Act: -0.0000
Data Index: 1497963 (The Pile)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5502. Min Range: -2.5502
Max Act: 1.4022. Min Act: -0.0000
Data Index: 479052 (The Pile)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5502. Min Range: -2.5502
Max Act: 1.3676. Min Act: -0.0000
Data Index: 1252364 (The Pile)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5502. Min Range: -2.5502
Max Act: 1.2942. Min Act: -0.0000
Data Index: 638842 (The Pile)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5502. Min Range: -2.5502
Max Act: 1.3380. Min Act: -0.0000
Data Index: 280549 (The Pile)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19