Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3208 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0106. Min Act: -0.0001
Data Index: 1987798 (The Pile)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0104. Min Act: -0.0001
Data Index: 1200937 (The Pile)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0101. Min Act: -0.0001
Data Index: 1504115 (The Pile)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0099. Min Act: -0.0001
Data Index: 324935 (The Pile)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0096. Min Act: -0.0001
Data Index: 1019798 (The Pile)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0096. Min Act: -0.0001
Data Index: 301529 (The Pile)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0096. Min Act: -0.0001
Data Index: 1672893 (The Pile)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0095. Min Act: -0.0001
Data Index: 1795705 (The Pile)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0094. Min Act: -0.0000
Data Index: 1586452 (The Pile)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0094. Min Act: -0.0001
Data Index: 1255043 (The Pile)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0094. Min Act: -0.0001
Data Index: 964659 (The Pile)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0094. Min Act: -0.0001
Data Index: 1899005 (The Pile)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0094. Min Act: -0.0001
Data Index: 289940 (The Pile)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0093. Min Act: -0.0001
Data Index: 1405049 (The Pile)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0093. Min Act: -0.0000
Data Index: 933857 (The Pile)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0093. Min Act: -0.0001
Data Index: 892943 (The Pile)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0093. Min Act: -0.0000
Data Index: 729625 (The Pile)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0092. Min Act: -0.0001
Data Index: 147301 (The Pile)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0092. Min Act: -0.0001
Data Index: 757855 (The Pile)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0106. Min Range: -0.0106
Max Act: 0.0092. Min Act: -0.0001
Data Index: 1088776 (The Pile)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19