Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3007 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.6935. Min Range: -2.6935
Max Act: 2.6935. Min Act: -0.0000
Data Index: 1288855 (The Pile)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.8661. Min Act: -0.0000
Data Index: 1591611 (The Pile)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.9671. Min Act: -0.0000
Data Index: 158726 (The Pile)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.7538. Min Act: -0.0000
Data Index: 1603175 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6935. Min Range: -2.6935
Max Act: 2.0623. Min Act: -0.0000
Data Index: 565352 (The Pile)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.9282. Min Act: -0.0000
Data Index: 1956299 (The Pile)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.8718. Min Act: -0.0000
Data Index: 1802493 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.9607. Min Act: -0.0000
Data Index: 957704 (The Pile)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.9135. Min Act: -0.0000
Data Index: 1199933 (The Pile)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.6999. Min Act: -0.0000
Data Index: 218733 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.6951. Min Act: -0.0000
Data Index: 1862196 (The Pile)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.8642. Min Act: -0.0000
Data Index: 864045 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.7563. Min Act: -0.0000
Data Index: 1574391 (The Pile)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.7261. Min Act: -0.0000
Data Index: 1025517 (The Pile)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.7300. Min Act: -0.0000
Data Index: 534003 (The Pile)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.7224. Min Act: -0.0000
Data Index: 569089 (The Pile)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.8233. Min Act: -0.0000
Data Index: 568840 (The Pile)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.7176. Min Act: -0.0000
Data Index: 713104 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.6997. Min Act: -0.0000
Data Index: 728717 (The Pile)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6935. Min Range: -2.6935
Max Act: 1.6991. Min Act: -0.0000
Data Index: 929844 (The Pile)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19