Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2578 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.1461. Min Range: -1.1461
Max Act: 1.1440. Min Act: -0.0001
Data Index: 511694 (The Pile)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1461. Min Range: -1.1461
Max Act: 1.1461. Min Act: -0.0001
Data Index: 94984 (The Pile)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1461. Min Range: -1.1461
Max Act: 1.0018. Min Act: -0.0001
Data Index: 1172240 (The Pile)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1461. Min Range: -1.1461
Max Act: 0.9418. Min Act: -0.0001
Data Index: 1346916 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1461. Min Range: -1.1461
Max Act: 0.9403. Min Act: -0.0001
Data Index: 419847 (The Pile)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1461. Min Range: -1.1461
Max Act: 0.9695. Min Act: -0.0001
Data Index: 1486715 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1461. Min Range: -1.1461
Max Act: 0.9270. Min Act: -0.0001
Data Index: 1468732 (The Pile)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1461. Min Range: -1.1461
Max Act: 0.9445. Min Act: -0.0001
Data Index: 1915181 (The Pile)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1461. Min Range: -1.1461
Max Act: 0.8644. Min Act: -0.0001
Data Index: 1720446 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1461. Min Range: -1.1461
Max Act: 0.8807. Min Act: -0.0001
Data Index: 548378 (The Pile)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1461. Min Range: -1.1461
Max Act: 0.9683. Min Act: -0.0001
Data Index: 1970991 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1461. Min Range: -1.1461
Max Act: 0.8745. Min Act: -0.0001
Data Index: 617975 (The Pile)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1461. Min Range: -1.1461
Max Act: 0.8182. Min Act: -0.0001
Data Index: 728421 (The Pile)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1461. Min Range: -1.1461
Max Act: 0.8671. Min Act: -0.0001
Data Index: 1931728 (The Pile)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1461. Min Range: -1.1461
Max Act: 0.9087. Min Act: -0.0002
Data Index: 1508692 (The Pile)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1461. Min Range: -1.1461
Max Act: 0.8604. Min Act: -0.0001
Data Index: 1807904 (The Pile)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1461. Min Range: -1.1461
Max Act: 0.8500. Min Act: -0.0001
Data Index: 1271746 (The Pile)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1461. Min Range: -1.1461
Max Act: 0.8698. Min Act: -0.0001
Data Index: 965540 (The Pile)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1461. Min Range: -1.1461
Max Act: 0.7958. Min Act: -0.0001
Data Index: 1289442 (The Pile)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1461. Min Range: -1.1461
Max Act: 0.8903. Min Act: -0.0001
Data Index: 633171 (The Pile)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19