Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 577 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0100. Min Act: -0.0002
Data Index: 503920 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0100. Min Act: -0.0002
Data Index: 1517326 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0097. Min Act: -0.0002
Data Index: 1344744 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0101. Min Act: -0.0002
Data Index: 426844 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0097. Min Act: -0.0003
Data Index: 1753 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0098. Min Act: -0.0002
Data Index: 16291 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0099. Min Act: -0.0003
Data Index: 910064 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0096. Min Act: -0.0002
Data Index: 1648184 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0097. Min Act: -0.0002
Data Index: 1245352 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0095. Min Act: -0.0002
Data Index: 881483 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0095. Min Act: -0.0002
Data Index: 1004298 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0092. Min Act: -0.0002
Data Index: 618683 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0093. Min Act: -0.0003
Data Index: 1658291 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0094. Min Act: -0.0002
Data Index: 1881301 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0092. Min Act: -0.0002
Data Index: 533365 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0091. Min Act: -0.0002
Data Index: 661409 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0089. Min Act: -0.0002
Data Index: 590193 (The Pile)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0093. Min Act: -0.0002
Data Index: 34753 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0088. Min Act: -0.0003
Data Index: 579194 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0101. Min Range: -0.0101
Max Act: 0.0091. Min Act: -0.0002
Data Index: 181725 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19