Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 769 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.5047. Min Act: -0.0001
Data Index: 1969148 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.4648. Min Act: -0.0001
Data Index: 51874 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.4627. Min Act: -0.0001
Data Index: 1492418 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.4581. Min Act: -0.0001
Data Index: 350847 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.4667. Min Act: -0.0001
Data Index: 39860 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.4229. Min Act: -0.0001
Data Index: 1017313 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.4908. Min Act: -0.0001
Data Index: 1112531 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.4577. Min Act: -0.0001
Data Index: 494012 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.4869. Min Act: -0.0001
Data Index: 304251 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.4168. Min Act: -0.0001
Data Index: 545913 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.4417. Min Act: -0.0001
Data Index: 342860 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.4145. Min Act: -0.0001
Data Index: 712599 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.3843. Min Act: -0.0001
Data Index: 16188 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.4246. Min Act: -0.0001
Data Index: 1180898 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.4246. Min Act: -0.0001
Data Index: 391264 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.4307. Min Act: -0.0001
Data Index: 616627 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.3954. Min Act: -0.0001
Data Index: 1915437 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.3900. Min Act: -0.0001
Data Index: 61846 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.4035. Min Act: -0.0001
Data Index: 1413631 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5047. Min Range: -0.5047
Max Act: 0.4271. Min Act: -0.0001
Data Index: 1334825 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19