Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1713 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.8568. Min Act: -0.0001
Data Index: 1042776 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.7835. Min Act: -0.0001
Data Index: 1558877 (Python Code)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.8214. Min Act: -0.0001
Data Index: 1119910 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.8107. Min Act: -0.0001
Data Index: 569994 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.8180. Min Act: -0.0001
Data Index: 1103983 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.8120. Min Act: -0.0001
Data Index: 790094 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.8211. Min Act: -0.0001
Data Index: 114223 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.8139. Min Act: -0.0001
Data Index: 870626 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.7635. Min Act: -0.0001
Data Index: 28809 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.7143. Min Act: -0.0001
Data Index: 1447182 (Python Code)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.7854. Min Act: -0.0001
Data Index: 92044 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.7355. Min Act: -0.0001
Data Index: 739853 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.7610. Min Act: -0.0001
Data Index: 831201 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.7557. Min Act: -0.0001
Data Index: 525918 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.7747. Min Act: -0.0001
Data Index: 200490 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.7728. Min Act: -0.0001
Data Index: 384344 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.7633. Min Act: -0.0001
Data Index: 453070 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.7972. Min Act: -0.0001
Data Index: 475045 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.7911. Min Act: -0.0001
Data Index: 676742 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8568. Min Range: -0.8568
Max Act: 0.7418. Min Act: -0.0001
Data Index: 518199 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19