Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: The Pile
Neuron 706 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')
Text #0
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.6637. Min Act: -0.0001
Data Index: 1352629 (The Pile)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.6587. Min Act: -0.0001
Data Index: 1449988 (The Pile)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.6321. Min Act: -0.0001
Data Index: 69728 (The Pile)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.6455. Min Act: -0.0001
Data Index: 1587401 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.5985. Min Act: -0.0001
Data Index: 41979 (The Pile)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.6328. Min Act: -0.0001
Data Index: 1482380 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.5930. Min Act: -0.0001
Data Index: 889090 (The Pile)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.5914. Min Act: -0.0001
Data Index: 1813965 (The Pile)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.6006. Min Act: -0.0001
Data Index: 980581 (The Pile)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.6182. Min Act: -0.0001
Data Index: 1101819 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.6191. Min Act: -0.0001
Data Index: 453547 (The Pile)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.6147. Min Act: -0.0001
Data Index: 224338 (The Pile)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.6150. Min Act: -0.0001
Data Index: 670421 (The Pile)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.6353. Min Act: -0.0001
Data Index: 977135 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.6106. Min Act: -0.0001
Data Index: 1366295 (The Pile)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.6083. Min Act: -0.0001
Data Index: 1443754 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.6077. Min Act: -0.0001
Data Index: 469898 (The Pile)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.5672. Min Act: -0.0001
Data Index: 567597 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.6046. Min Act: -0.0001
Data Index: 805636 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6637. Min Range: -0.6637
Max Act: 0.6051. Min Act: -0.0001
Data Index: 1546552 (The Pile)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19