Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1322 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.8016. Min Act: -0.0000
Data Index: 1787608 (The Pile)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8016. Min Range: -3.8016
Max Act: 3.3788. Min Act: -0.0000
Data Index: 1824874 (The Pile)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.7180. Min Act: -0.0000
Data Index: 773077 (The Pile)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.9602. Min Act: -0.0000
Data Index: 1778768 (The Pile)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.7878. Min Act: -0.0000
Data Index: 147752 (The Pile)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.7963. Min Act: -0.0000
Data Index: 119929 (The Pile)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.6312. Min Act: -0.0000
Data Index: 1982533 (The Pile)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.7237. Min Act: -0.0000
Data Index: 906170 (The Pile)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.5556. Min Act: -0.0000
Data Index: 1226501 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.5531. Min Act: -0.0000
Data Index: 156533 (The Pile)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.4115. Min Act: -0.0000
Data Index: 1655977 (The Pile)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.4816. Min Act: -0.0000
Data Index: 777672 (The Pile)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.4538. Min Act: -0.0000
Data Index: 640410 (The Pile)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.0371. Min Act: -0.0000
Data Index: 1545139 (The Pile)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.1803. Min Act: -0.0000
Data Index: 160179 (The Pile)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.2956. Min Act: -0.0000
Data Index: 345801 (The Pile)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.1807. Min Act: -0.0000
Data Index: 675243 (The Pile)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.4133. Min Act: -0.0000
Data Index: 102392 (The Pile)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.3945. Min Act: -0.0000
Data Index: 843694 (The Pile)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8016. Min Range: -3.8016
Max Act: 2.2537. Min Act: -0.0000
Data Index: 188393 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19