Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1005 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.1080. Min Range: -1.1080
Max Act: 1.1080. Min Act: -0.0001
Data Index: 479248 (The Pile)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1080. Min Range: -1.1080
Max Act: 1.0462. Min Act: -0.0001
Data Index: 1392663 (The Pile)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1080. Min Range: -1.1080
Max Act: 1.0921. Min Act: -0.0001
Data Index: 206162 (The Pile)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1080. Min Range: -1.1080
Max Act: 1.0184. Min Act: -0.0001
Data Index: 149409 (The Pile)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1080. Min Range: -1.1080
Max Act: 0.9919. Min Act: -0.0001
Data Index: 359580 (The Pile)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1080. Min Range: -1.1080
Max Act: 0.9481. Min Act: -0.0001
Data Index: 488708 (The Pile)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1080. Min Range: -1.1080
Max Act: 0.8998. Min Act: -0.0001
Data Index: 675184 (The Pile)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1080. Min Range: -1.1080
Max Act: 0.9057. Min Act: -0.0001
Data Index: 62374 (The Pile)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1080. Min Range: -1.1080
Max Act: 0.9037. Min Act: -0.0001
Data Index: 1183817 (The Pile)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1080. Min Range: -1.1080
Max Act: 0.9915. Min Act: -0.0001
Data Index: 1248912 (The Pile)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1080. Min Range: -1.1080
Max Act: 0.9009. Min Act: -0.0001
Data Index: 1109688 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1080. Min Range: -1.1080
Max Act: 0.9493. Min Act: -0.0001
Data Index: 519891 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1080. Min Range: -1.1080
Max Act: 0.9300. Min Act: -0.0001
Data Index: 130928 (The Pile)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1080. Min Range: -1.1080
Max Act: 0.8866. Min Act: -0.0001
Data Index: 481622 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1080. Min Range: -1.1080
Max Act: 0.9782. Min Act: -0.0001
Data Index: 745730 (The Pile)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1080. Min Range: -1.1080
Max Act: 0.9083. Min Act: -0.0001
Data Index: 1585073 (The Pile)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1080. Min Range: -1.1080
Max Act: 0.9095. Min Act: -0.0001
Data Index: 1899385 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1080. Min Range: -1.1080
Max Act: 0.9684. Min Act: -0.0001
Data Index: 167666 (The Pile)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1080. Min Range: -1.1080
Max Act: 0.8104. Min Act: -0.0001
Data Index: 459579 (The Pile)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1080. Min Range: -1.1080
Max Act: 1.0070. Min Act: -0.0001
Data Index: 423251 (The Pile)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19