Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 762 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.1049. Min Range: -6.1049
Max Act: 6.1049. Min Act: -0.1700
Data Index: 410597 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1049. Min Range: -6.1049
Max Act: 6.0736. Min Act: -0.1700
Data Index: 979927 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.9486. Min Act: -0.1700
Data Index: 320653 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.8861. Min Act: -0.1700
Data Index: 671133 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.9174. Min Act: -0.1700
Data Index: 400913 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.9174. Min Act: -0.1700
Data Index: 858858 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.8549. Min Act: -0.1700
Data Index: 1086231 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.9174. Min Act: -0.1700
Data Index: 658848 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.9174. Min Act: -0.1700
Data Index: 809282 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.8549. Min Act: -0.1700
Data Index: 783662 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.8861. Min Act: -0.1700
Data Index: 351144 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.8236. Min Act: -0.1700
Data Index: 1093686 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.8549. Min Act: -0.1700
Data Index: 958910 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.8236. Min Act: -0.1700
Data Index: 181094 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.8236. Min Act: -0.1700
Data Index: 619068 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.9174. Min Act: -0.1700
Data Index: 20690 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.7924. Min Act: -0.1700
Data Index: 890908 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.8549. Min Act: -0.1700
Data Index: 505438 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.8549. Min Act: -0.1700
Data Index: 250780 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1049. Min Range: -6.1049
Max Act: 5.8236. Min Act: -0.1700
Data Index: 425775 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19