Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2366 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.7540. Min Act: 0.0000
Data Index: 1604434 (The Pile)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.4449. Min Act: -0.0000
Data Index: 1833189 (The Pile)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.5244. Min Act: -0.0000
Data Index: 529200 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.4128. Min Act: -0.0000
Data Index: 1699829 (The Pile)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.2811. Min Act: -0.0000
Data Index: 45751 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.1942. Min Act: -0.0000
Data Index: 247184 (The Pile)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.1643. Min Act: -0.0000
Data Index: 552401 (The Pile)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.2155. Min Act: -0.0000
Data Index: 105395 (The Pile)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.2107. Min Act: -0.0000
Data Index: 481486 (The Pile)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.1235. Min Act: -0.0000
Data Index: 1731539 (The Pile)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.1877. Min Act: -0.0000
Data Index: 1193988 (The Pile)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.1868. Min Act: -0.0000
Data Index: 19423 (The Pile)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.1622. Min Act: -0.0000
Data Index: 675846 (The Pile)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.1582. Min Act: -0.0000
Data Index: 816427 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.0851. Min Act: -0.0000
Data Index: 1163583 (The Pile)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.2049. Min Act: -0.0000
Data Index: 219057 (The Pile)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.1075. Min Act: -0.0000
Data Index: 1396415 (The Pile)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.2495. Min Act: -0.0000
Data Index: 167618 (The Pile)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.0915. Min Act: -0.0000
Data Index: 579410 (The Pile)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7540. Min Range: -1.7540
Max Act: 1.0339. Min Act: -0.0000
Data Index: 804696 (The Pile)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19