Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 4057 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0407. Min Act: -0.0002
Data Index: 619535 (The Pile)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0360. Min Act: -0.0002
Data Index: 364385 (The Pile)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0384. Min Act: -0.0002
Data Index: 217936 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0384. Min Act: -0.0002
Data Index: 109014 (The Pile)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0337. Min Act: -0.0002
Data Index: 22321 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0337. Min Act: -0.0002
Data Index: 119940 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0337. Min Act: -0.0002
Data Index: 103858 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0337. Min Act: -0.0002
Data Index: 385895 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0337. Min Act: -0.0002
Data Index: 81857 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0337. Min Act: -0.0002
Data Index: 101728 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0337. Min Act: -0.0002
Data Index: 343230 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0337. Min Act: -0.0002
Data Index: 73151 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0337. Min Act: -0.0002
Data Index: 62262 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0337. Min Act: -0.0002
Data Index: 232068 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0337. Min Act: -0.0002
Data Index: 213372 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0337. Min Act: -0.0002
Data Index: 516396 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0337. Min Act: -0.0002
Data Index: 389107 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0337. Min Act: -0.0002
Data Index: 310799 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0337. Min Act: -0.0002
Data Index: 254073 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0407. Min Range: -0.0407
Max Act: 0.0337. Min Act: -0.0002
Data Index: 250816 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19