Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1803 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.7879. Min Act: -0.0000
Data Index: 671838 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.5509. Min Act: -0.0000
Data Index: 912245 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.6278. Min Act: -0.0000
Data Index: 978316 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.4861. Min Act: -0.0000
Data Index: 457292 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.5481. Min Act: -0.0000
Data Index: 659489 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.5224. Min Act: -0.0000
Data Index: 1512786 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.4494. Min Act: -0.0000
Data Index: 1637885 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.4903. Min Act: -0.0000
Data Index: 564144 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.4968. Min Act: -0.0000
Data Index: 1146765 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.3945. Min Act: -0.0000
Data Index: 996516 (The Pile)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.3592. Min Act: -0.0000
Data Index: 1944755 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.3850. Min Act: -0.0000
Data Index: 1325925 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.3996. Min Act: -0.0000
Data Index: 1888838 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.3356. Min Act: -0.0000
Data Index: 1942468 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.4800. Min Act: -0.0000
Data Index: 1581509 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.3828. Min Act: -0.0000
Data Index: 994113 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.3332. Min Act: -0.0000
Data Index: 1312083 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.3575. Min Act: -0.0000
Data Index: 316014 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.3312. Min Act: -0.0000
Data Index: 665745 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7879. Min Range: -1.7879
Max Act: 1.3225. Min Act: -0.0000
Data Index: 1207617 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19