Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3106 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.3968. Min Range: -2.3968
Max Act: 2.2924. Min Act: -0.0001
Data Index: 598125 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3968. Min Range: -2.3968
Max Act: 2.3968. Min Act: -0.0001
Data Index: 253402 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3968. Min Range: -2.3968
Max Act: 2.0257. Min Act: -0.0001
Data Index: 633589 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3968. Min Range: -2.3968
Max Act: 2.2516. Min Act: -0.0001
Data Index: 944033 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3968. Min Range: -2.3968
Max Act: 1.9928. Min Act: -0.0001
Data Index: 1336146 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3968. Min Range: -2.3968
Max Act: 1.9717. Min Act: -0.0001
Data Index: 686442 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3968. Min Range: -2.3968
Max Act: 1.8984. Min Act: -0.0001
Data Index: 423156 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3968. Min Range: -2.3968
Max Act: 1.9696. Min Act: -0.0001
Data Index: 323907 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3968. Min Range: -2.3968
Max Act: 1.9703. Min Act: -0.0001
Data Index: 324130 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3968. Min Range: -2.3968
Max Act: 2.0362. Min Act: -0.0001
Data Index: 923987 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3968. Min Range: -2.3968
Max Act: 1.9430. Min Act: -0.0001
Data Index: 540383 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3968. Min Range: -2.3968
Max Act: 1.9279. Min Act: -0.0001
Data Index: 301139 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3968. Min Range: -2.3968
Max Act: 1.9324. Min Act: -0.0001
Data Index: 1267454 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3968. Min Range: -2.3968
Max Act: 1.9327. Min Act: -0.0001
Data Index: 205667 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3968. Min Range: -2.3968
Max Act: 1.7973. Min Act: -0.0001
Data Index: 522211 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3968. Min Range: -2.3968
Max Act: 2.0201. Min Act: -0.0001
Data Index: 953770 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3968. Min Range: -2.3968
Max Act: 2.0122. Min Act: -0.0001
Data Index: 1191201 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3968. Min Range: -2.3968
Max Act: 1.9846. Min Act: -0.0001
Data Index: 214897 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3968. Min Range: -2.3968
Max Act: 1.9019. Min Act: -0.0001
Data Index: 1604874 (Python Code)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3968. Min Range: -2.3968
Max Act: 1.9950. Min Act: -0.0001
Data Index: 1258043 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19