Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 1652 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.7719. Min Act: -0.0001
Data Index: 1915544 (The Pile)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.7290. Min Act: -0.0000
Data Index: 1190409 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.7221. Min Act: 0.0000
Data Index: 1699600 (The Pile)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.7172. Min Act: -0.0001
Data Index: 71077 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.6720. Min Act: -0.0001
Data Index: 860598 (The Pile)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.7050. Min Act: -0.0001
Data Index: 1207418 (The Pile)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.6834. Min Act: 0.0000
Data Index: 1795828 (The Pile)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.6717. Min Act: -0.0001
Data Index: 682977 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.6863. Min Act: -0.0001
Data Index: 821821 (The Pile)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.7305. Min Act: -0.0001
Data Index: 41687 (The Pile)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.7208. Min Act: -0.0001
Data Index: 1914859 (The Pile)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.6956. Min Act: -0.0001
Data Index: 477131 (The Pile)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.6692. Min Act: -0.0001
Data Index: 368829 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.6688. Min Act: -0.0001
Data Index: 1941335 (The Pile)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.6446. Min Act: -0.0001
Data Index: 1442974 (The Pile)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.6404. Min Act: -0.0001
Data Index: 297875 (The Pile)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.6980. Min Act: -0.0000
Data Index: 1254025 (The Pile)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.6584. Min Act: -0.0001
Data Index: 517919 (The Pile)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.6678. Min Act: -0.0000
Data Index: 1627832 (The Pile)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7719. Min Range: -0.7719
Max Act: 0.6374. Min Act: -0.0001
Data Index: 1202090 (The Pile)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19