Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2395 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.1281. Min Range: -1.1281
Max Act: 1.1281. Min Act: -0.0001
Data Index: 452875 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1281. Min Range: -1.1281
Max Act: 0.9812. Min Act: -0.0001
Data Index: 295593 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1281. Min Range: -1.1281
Max Act: 1.0370. Min Act: -0.0001
Data Index: 1055420 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1281. Min Range: -1.1281
Max Act: 1.0742. Min Act: -0.0001
Data Index: 982742 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1281. Min Range: -1.1281
Max Act: 1.1029. Min Act: -0.0001
Data Index: 607949 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1281. Min Range: -1.1281
Max Act: 1.0904. Min Act: -0.0001
Data Index: 656967 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1281. Min Range: -1.1281
Max Act: 0.9990. Min Act: -0.0001
Data Index: 1102215 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1281. Min Range: -1.1281
Max Act: 1.0760. Min Act: -0.0001
Data Index: 946997 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1281. Min Range: -1.1281
Max Act: 0.9892. Min Act: -0.0001
Data Index: 711303 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1281. Min Range: -1.1281
Max Act: 0.9778. Min Act: -0.0001
Data Index: 1314981 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1281. Min Range: -1.1281
Max Act: 0.9811. Min Act: -0.0001
Data Index: 485843 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1281. Min Range: -1.1281
Max Act: 1.0528. Min Act: -0.0001
Data Index: 547954 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1281. Min Range: -1.1281
Max Act: 0.9780. Min Act: -0.0001
Data Index: 239510 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1281. Min Range: -1.1281
Max Act: 0.9727. Min Act: -0.0001
Data Index: 707930 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1281. Min Range: -1.1281
Max Act: 1.0086. Min Act: -0.0001
Data Index: 650439 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1281. Min Range: -1.1281
Max Act: 1.0120. Min Act: -0.0001
Data Index: 311652 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1281. Min Range: -1.1281
Max Act: 0.9829. Min Act: -0.0001
Data Index: 152075 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1281. Min Range: -1.1281
Max Act: 1.0041. Min Act: -0.0001
Data Index: 287513 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1281. Min Range: -1.1281
Max Act: 1.0526. Min Act: -0.0001
Data Index: 984547 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1281. Min Range: -1.1281
Max Act: 0.9165. Min Act: -0.0001
Data Index: 759921 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19