Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 295 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.5017. Min Act: -0.1700
Data Index: 843675 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.4855. Min Act: -0.1700
Data Index: 426206 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.4531. Min Act: -0.1700
Data Index: 376682 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.4368. Min Act: -0.1700
Data Index: 1304905 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.4531. Min Act: -0.1700
Data Index: 848514 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.4043. Min Act: -0.1700
Data Index: 50149 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.4043. Min Act: -0.1700
Data Index: 944067 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.4043. Min Act: -0.1700
Data Index: 647117 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.4043. Min Act: -0.1700
Data Index: 1029976 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.4043. Min Act: -0.1700
Data Index: 1076861 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.4043. Min Act: -0.1700
Data Index: 1348656 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.4043. Min Act: -0.1700
Data Index: 131851 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.3879. Min Act: -0.1700
Data Index: 773763 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.3716. Min Act: -0.1700
Data Index: 985305 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.3716. Min Act: -0.1700
Data Index: 145757 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.3716. Min Act: -0.1700
Data Index: 1250563 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.3716. Min Act: -0.1700
Data Index: 1222619 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.3552. Min Act: -0.1700
Data Index: 145520 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.3552. Min Act: -0.1700
Data Index: 511358 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5017. Min Range: -2.5017
Max Act: 2.3552. Min Act: -0.1700
Data Index: 1202211 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19