Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1458 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.2617. Min Act: -0.0001
Data Index: 1230372 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.2150. Min Act: -0.0001
Data Index: 1490098 (The Pile)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.2124. Min Act: -0.0001
Data Index: 1491104 (The Pile)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.2243. Min Act: -0.0001
Data Index: 844007 (The Pile)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.2046. Min Act: -0.0001
Data Index: 606098 (The Pile)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.2144. Min Act: -0.0001
Data Index: 96104 (The Pile)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.2105. Min Act: -0.0001
Data Index: 1432262 (The Pile)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.2118. Min Act: -0.0001
Data Index: 1068300 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.2040. Min Act: -0.0001
Data Index: 72014 (The Pile)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.2053. Min Act: -0.0001
Data Index: 1655821 (The Pile)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.1956. Min Act: -0.0001
Data Index: 1920389 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.1987. Min Act: -0.0001
Data Index: 1723615 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.2022. Min Act: -0.0001
Data Index: 1644550 (The Pile)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.1967. Min Act: -0.0001
Data Index: 1940967 (The Pile)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.1904. Min Act: -0.0001
Data Index: 1147012 (The Pile)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.2018. Min Act: -0.0001
Data Index: 171271 (The Pile)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.1895. Min Act: -0.0001
Data Index: 1051454 (The Pile)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.1937. Min Act: -0.0001
Data Index: 154725 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.1867. Min Act: -0.0001
Data Index: 1475644 (The Pile)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2617. Min Range: -0.2617
Max Act: 0.1923. Min Act: -0.0001
Data Index: 8161 (The Pile)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19