Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1741 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.6096. Min Range: -2.6096
Max Act: 2.5939. Min Act: -0.0000
Data Index: 1170853 (The Pile)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6096. Min Range: -2.6096
Max Act: 2.6096. Min Act: -0.0000
Data Index: 517396 (The Pile)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6096. Min Range: -2.6096
Max Act: 2.0553. Min Act: -0.0000
Data Index: 876657 (The Pile)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6096. Min Range: -2.6096
Max Act: 2.0579. Min Act: -0.0000
Data Index: 1912771 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6096. Min Range: -2.6096
Max Act: 2.0582. Min Act: -0.0000
Data Index: 314329 (The Pile)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6096. Min Range: -2.6096
Max Act: 2.0557. Min Act: -0.0000
Data Index: 912188 (The Pile)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6096. Min Range: -2.6096
Max Act: 1.9357. Min Act: -0.0000
Data Index: 176625 (The Pile)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6096. Min Range: -2.6096
Max Act: 1.8705. Min Act: -0.0000
Data Index: 413839 (The Pile)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6096. Min Range: -2.6096
Max Act: 1.8301. Min Act: -0.0000
Data Index: 993915 (The Pile)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6096. Min Range: -2.6096
Max Act: 1.9339. Min Act: -0.0000
Data Index: 757106 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6096. Min Range: -2.6096
Max Act: 1.8986. Min Act: -0.0000
Data Index: 252615 (The Pile)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6096. Min Range: -2.6096
Max Act: 1.8921. Min Act: -0.0000
Data Index: 1089644 (The Pile)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6096. Min Range: -2.6096
Max Act: 2.0015. Min Act: -0.0000
Data Index: 1132203 (The Pile)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6096. Min Range: -2.6096
Max Act: 1.8615. Min Act: -0.0000
Data Index: 232076 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6096. Min Range: -2.6096
Max Act: 1.7628. Min Act: -0.0000
Data Index: 124502 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6096. Min Range: -2.6096
Max Act: 1.8284. Min Act: -0.0000
Data Index: 1008739 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6096. Min Range: -2.6096
Max Act: 1.7390. Min Act: -0.0000
Data Index: 804914 (The Pile)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6096. Min Range: -2.6096
Max Act: 1.8293. Min Act: -0.0000
Data Index: 1358131 (The Pile)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6096. Min Range: -2.6096
Max Act: 1.8229. Min Act: -0.0000
Data Index: 1185036 (The Pile)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6096. Min Range: -2.6096
Max Act: 1.7980. Min Act: -0.0000
Data Index: 1018221 (The Pile)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19