Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1663 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.2030. Min Range: -2.2030
Max Act: 2.2030. Min Act: -0.0000
Data Index: 1357649 (The Pile)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.9652. Min Act: -0.0000
Data Index: 1717410 (The Pile)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.8655. Min Act: -0.0000
Data Index: 317447 (The Pile)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.9152. Min Act: -0.0000
Data Index: 1924227 (The Pile)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2030. Min Range: -2.2030
Max Act: 2.0160. Min Act: -0.0000
Data Index: 860114 (The Pile)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.9565. Min Act: -0.0000
Data Index: 787373 (The Pile)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.9516. Min Act: -0.0000
Data Index: 709465 (The Pile)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.9799. Min Act: -0.0000
Data Index: 1961258 (The Pile)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.9238. Min Act: -0.0000
Data Index: 888075 (The Pile)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.8244. Min Act: -0.0000
Data Index: 1971754 (The Pile)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.7167. Min Act: -0.0000
Data Index: 1058825 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.9122. Min Act: -0.0000
Data Index: 611656 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.8065. Min Act: -0.0000
Data Index: 28373 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.7808. Min Act: -0.0000
Data Index: 422945 (The Pile)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.6820. Min Act: -0.0000
Data Index: 210012 (The Pile)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.8435. Min Act: -0.0000
Data Index: 1915935 (The Pile)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.6603. Min Act: -0.0000
Data Index: 647433 (The Pile)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.7452. Min Act: -0.0000
Data Index: 136848 (The Pile)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.6001. Min Act: -0.0000
Data Index: 510944 (The Pile)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.6013. Min Act: -0.0000
Data Index: 1436978 (The Pile)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19