Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 607 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.0268. Min Range: -2.0268
Max Act: 2.0268. Min Act: -0.0000
Data Index: 150409 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.5733. Min Act: -0.0001
Data Index: 627613 (The Pile)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.5493. Min Act: -0.0000
Data Index: 1494350 (The Pile)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.5229. Min Act: -0.0000
Data Index: 806519 (The Pile)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.4946. Min Act: -0.0000
Data Index: 848255 (The Pile)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.5231. Min Act: -0.0000
Data Index: 741039 (The Pile)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.4238. Min Act: -0.0000
Data Index: 514364 (The Pile)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.4721. Min Act: -0.0000
Data Index: 801683 (The Pile)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.4529. Min Act: -0.0000
Data Index: 1545530 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.4090. Min Act: -0.0000
Data Index: 866010 (The Pile)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.5726. Min Act: -0.0000
Data Index: 1057530 (The Pile)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.4214. Min Act: -0.0000
Data Index: 595220 (The Pile)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.4284. Min Act: -0.0000
Data Index: 537166 (The Pile)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.5783. Min Act: -0.0000
Data Index: 101534 (The Pile)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.3963. Min Act: -0.0000
Data Index: 1294669 (The Pile)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.4100. Min Act: -0.0000
Data Index: 205632 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.3237. Min Act: -0.0000
Data Index: 1658873 (The Pile)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.3643. Min Act: -0.0000
Data Index: 1270195 (The Pile)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.2813. Min Act: -0.0000
Data Index: 1671118 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0268. Min Range: -2.0268
Max Act: 1.3819. Min Act: -0.0000
Data Index: 1518255 (The Pile)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19