Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 466 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 14228 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 28072 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 13685 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 23524 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 13820 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 22144 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 13001 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 22137 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 21378 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 10566 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 28662 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 20230 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 19392 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 9112 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 18445 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 7566 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 6445 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 15849 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 4409 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0330. Min Range: -0.0330
Max Act: 0.0330. Min Act: -0.0002
Data Index: 6282 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19