Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2675 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.0853. Min Range: -1.0853
Max Act: 1.0853. Min Act: -0.0001
Data Index: 677605 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0853. Min Range: -1.0853
Max Act: 1.0754. Min Act: -0.0001
Data Index: 170375 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0853. Min Range: -1.0853
Max Act: 1.0851. Min Act: -0.0001
Data Index: 1129061 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0853. Min Range: -1.0853
Max Act: 1.0320. Min Act: -0.0001
Data Index: 376613 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0853. Min Range: -1.0853
Max Act: 1.0565. Min Act: -0.0001
Data Index: 1337438 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0853. Min Range: -1.0853
Max Act: 1.0637. Min Act: -0.0001
Data Index: 784374 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0853. Min Range: -1.0853
Max Act: 1.0145. Min Act: -0.0001
Data Index: 188123 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0853. Min Range: -1.0853
Max Act: 1.0157. Min Act: -0.0001
Data Index: 805284 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0853. Min Range: -1.0853
Max Act: 1.0447. Min Act: -0.0001
Data Index: 156560 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0853. Min Range: -1.0853
Max Act: 1.0099. Min Act: -0.0001
Data Index: 1057291 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0853. Min Range: -1.0853
Max Act: 0.9787. Min Act: -0.0001
Data Index: 7857 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0853. Min Range: -1.0853
Max Act: 0.9732. Min Act: -0.0001
Data Index: 981439 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0853. Min Range: -1.0853
Max Act: 1.0092. Min Act: -0.0001
Data Index: 37070 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0853. Min Range: -1.0853
Max Act: 1.0084. Min Act: -0.0001
Data Index: 1215611 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0853. Min Range: -1.0853
Max Act: 1.0001. Min Act: -0.0001
Data Index: 996819 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0853. Min Range: -1.0853
Max Act: 0.9657. Min Act: -0.0001
Data Index: 797392 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0853. Min Range: -1.0853
Max Act: 0.9495. Min Act: -0.0001
Data Index: 721581 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0853. Min Range: -1.0853
Max Act: 0.9821. Min Act: -0.0001
Data Index: 840224 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0853. Min Range: -1.0853
Max Act: 1.0115. Min Act: -0.0001
Data Index: 839788 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0853. Min Range: -1.0853
Max Act: 0.9506. Min Act: -0.0001
Data Index: 1104515 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19