Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1936 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.8147. Min Act: -0.1700
Data Index: 561112 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.7030. Min Act: -0.1700
Data Index: 409120 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.7030. Min Act: -0.1700
Data Index: 400885 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.6709. Min Act: -0.1700
Data Index: 1312882 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.6709. Min Act: -0.1700
Data Index: 1237409 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.6709. Min Act: -0.1700
Data Index: 129277 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.6709. Min Act: -0.1700
Data Index: 245219 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.6549. Min Act: -0.1700
Data Index: 557212 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.6549. Min Act: -0.1700
Data Index: 634465 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.6228. Min Act: -0.1700
Data Index: 918030 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.6228. Min Act: -0.1700
Data Index: 336223 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.6228. Min Act: -0.1700
Data Index: 1029690 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.6389. Min Act: -0.1700
Data Index: 42533 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.6389. Min Act: -0.1700
Data Index: 799901 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.6389. Min Act: -0.1700
Data Index: 80825 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.6389. Min Act: -0.1700
Data Index: 6867 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.6228. Min Act: -0.1700
Data Index: 1162754 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.5906. Min Act: -0.1700
Data Index: 528679 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.5906. Min Act: -0.1700
Data Index: 634931 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8147. Min Range: -2.8147
Max Act: 2.6067. Min Act: -0.1700
Data Index: 357630 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19