Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1830 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.7695. Min Act: 0.0000
Data Index: 690331 (The Pile)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.7271. Min Act: -0.0000
Data Index: 1873063 (The Pile)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.6336. Min Act: -0.0000
Data Index: 1074342 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.6122. Min Act: -0.0000
Data Index: 538361 (The Pile)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.6261. Min Act: -0.0000
Data Index: 1997626 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.6088. Min Act: -0.0000
Data Index: 1603085 (The Pile)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.5461. Min Act: -0.0000
Data Index: 712363 (The Pile)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.4056. Min Act: 0.0000
Data Index: 282291 (The Pile)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.3994. Min Act: -0.0000
Data Index: 20404 (The Pile)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.4675. Min Act: -0.0000
Data Index: 1889310 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.5423. Min Act: -0.0000
Data Index: 98949 (The Pile)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.3389. Min Act: 0.0000
Data Index: 1323171 (The Pile)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.4834. Min Act: -0.0000
Data Index: 1729856 (The Pile)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.3684. Min Act: -0.0000
Data Index: 577352 (The Pile)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.3807. Min Act: -0.0000
Data Index: 127029 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.4606. Min Act: -0.0000
Data Index: 768232 (The Pile)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.3639. Min Act: 0.0000
Data Index: 118731 (The Pile)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.2725. Min Act: -0.0000
Data Index: 1124209 (The Pile)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.3577. Min Act: -0.0000
Data Index: 1132892 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7695. Min Range: -1.7695
Max Act: 1.2768. Min Act: 0.0000
Data Index: 1138629 (The Pile)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19