Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1726 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.6085. Min Act: -0.0001
Data Index: 804953 (The Pile)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.3153. Min Act: -0.0001
Data Index: 1330683 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.4212. Min Act: -0.0001
Data Index: 718218 (The Pile)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.3883. Min Act: -0.0001
Data Index: 214234 (The Pile)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.3139. Min Act: -0.0001
Data Index: 1922461 (The Pile)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.3855. Min Act: -0.0001
Data Index: 1918421 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.3898. Min Act: -0.0001
Data Index: 8602 (The Pile)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.3148. Min Act: -0.0001
Data Index: 1551251 (The Pile)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.2935. Min Act: -0.0001
Data Index: 1621583 (The Pile)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.3572. Min Act: -0.0001
Data Index: 1316092 (The Pile)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.3604. Min Act: -0.0001
Data Index: 245782 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.4137. Min Act: -0.0001
Data Index: 1580447 (The Pile)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.2109. Min Act: -0.0001
Data Index: 1816976 (The Pile)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.2993. Min Act: -0.0001
Data Index: 963023 (The Pile)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.3022. Min Act: -0.0001
Data Index: 83432 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.2096. Min Act: -0.0001
Data Index: 996867 (The Pile)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.1213. Min Act: -0.0001
Data Index: 1917625 (The Pile)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.1787. Min Act: -0.0001
Data Index: 890286 (The Pile)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.1840. Min Act: -0.0001
Data Index: 934608 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6085. Min Range: -1.6085
Max Act: 1.1208. Min Act: -0.0001
Data Index: 1402769 (The Pile)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19