Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2032 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.1578. Min Range: -1.1578
Max Act: 1.1161. Min Act: -0.0000
Data Index: 1957125 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1578. Min Range: -1.1578
Max Act: 1.1578. Min Act: -0.0000
Data Index: 136857 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1578. Min Range: -1.1578
Max Act: 1.0921. Min Act: -0.0000
Data Index: 1692222 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1578. Min Range: -1.1578
Max Act: 1.1193. Min Act: -0.0000
Data Index: 929540 (The Pile)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1578. Min Range: -1.1578
Max Act: 1.1090. Min Act: -0.0000
Data Index: 395177 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1578. Min Range: -1.1578
Max Act: 1.0750. Min Act: -0.0000
Data Index: 1358620 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1578. Min Range: -1.1578
Max Act: 1.0973. Min Act: -0.0000
Data Index: 1908076 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1578. Min Range: -1.1578
Max Act: 0.9945. Min Act: -0.0000
Data Index: 10438 (The Pile)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1578. Min Range: -1.1578
Max Act: 0.9744. Min Act: -0.0000
Data Index: 1600656 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1578. Min Range: -1.1578
Max Act: 1.0004. Min Act: -0.0000
Data Index: 653502 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1578. Min Range: -1.1578
Max Act: 0.9562. Min Act: -0.0000
Data Index: 244339 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1578. Min Range: -1.1578
Max Act: 0.9707. Min Act: -0.0001
Data Index: 1245910 (The Pile)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1578. Min Range: -1.1578
Max Act: 0.9646. Min Act: -0.0000
Data Index: 930762 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1578. Min Range: -1.1578
Max Act: 0.9625. Min Act: -0.0000
Data Index: 223448 (The Pile)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1578. Min Range: -1.1578
Max Act: 0.9284. Min Act: -0.0000
Data Index: 1473350 (The Pile)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1578. Min Range: -1.1578
Max Act: 0.9842. Min Act: -0.0000
Data Index: 348108 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1578. Min Range: -1.1578
Max Act: 0.9725. Min Act: -0.0000
Data Index: 128814 (The Pile)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1578. Min Range: -1.1578
Max Act: 0.9419. Min Act: -0.0000
Data Index: 733575 (The Pile)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1578. Min Range: -1.1578
Max Act: 0.9388. Min Act: -0.0000
Data Index: 1867736 (The Pile)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1578. Min Range: -1.1578
Max Act: 0.9365. Min Act: -0.0001
Data Index: 1932053 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19