Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 380 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.4045. Min Range: -1.4045
Max Act: 1.4045. Min Act: -0.0000
Data Index: 779626 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4045. Min Range: -1.4045
Max Act: 1.3395. Min Act: -0.0000
Data Index: 2070 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4045. Min Range: -1.4045
Max Act: 1.2412. Min Act: -0.0000
Data Index: 144969 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4045. Min Range: -1.4045
Max Act: 1.1050. Min Act: -0.0000
Data Index: 1300533 (The Pile)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4045. Min Range: -1.4045
Max Act: 1.1049. Min Act: -0.0000
Data Index: 1365344 (The Pile)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4045. Min Range: -1.4045
Max Act: 1.0140. Min Act: -0.0000
Data Index: 1092609 (The Pile)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4045. Min Range: -1.4045
Max Act: 1.0652. Min Act: -0.0000
Data Index: 1407736 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4045. Min Range: -1.4045
Max Act: 1.0616. Min Act: -0.0000
Data Index: 1893822 (The Pile)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4045. Min Range: -1.4045
Max Act: 1.0039. Min Act: -0.0000
Data Index: 1230397 (The Pile)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4045. Min Range: -1.4045
Max Act: 0.9936. Min Act: -0.0000
Data Index: 833147 (The Pile)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4045. Min Range: -1.4045
Max Act: 0.9840. Min Act: -0.0000
Data Index: 385438 (The Pile)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4045. Min Range: -1.4045
Max Act: 1.0007. Min Act: -0.0000
Data Index: 752785 (The Pile)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4045. Min Range: -1.4045
Max Act: 0.9765. Min Act: -0.0000
Data Index: 923298 (The Pile)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4045. Min Range: -1.4045
Max Act: 0.9135. Min Act: -0.0000
Data Index: 355623 (The Pile)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4045. Min Range: -1.4045
Max Act: 0.9250. Min Act: -0.0000
Data Index: 1147558 (The Pile)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4045. Min Range: -1.4045
Max Act: 0.8989. Min Act: -0.0000
Data Index: 1510234 (The Pile)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4045. Min Range: -1.4045
Max Act: 0.8767. Min Act: -0.0000
Data Index: 605146 (The Pile)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4045. Min Range: -1.4045
Max Act: 0.8767. Min Act: -0.0000
Data Index: 229690 (The Pile)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4045. Min Range: -1.4045
Max Act: 0.8217. Min Act: -0.0000
Data Index: 939336 (The Pile)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4045. Min Range: -1.4045
Max Act: 0.7945. Min Act: -0.0000
Data Index: 1863673 (The Pile)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19