Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 19 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.9800. Min Act: -0.1700
Data Index: 1110647 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.9642. Min Act: -0.1700
Data Index: 679971 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.9642. Min Act: -0.1700
Data Index: 379547 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.9484. Min Act: -0.1700
Data Index: 1349405 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.9484. Min Act: -0.1700
Data Index: 37491 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.9325. Min Act: -0.1700
Data Index: 1194889 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.9325. Min Act: -0.1700
Data Index: 981211 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.9167. Min Act: -0.1700
Data Index: 995868 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.8850. Min Act: -0.1700
Data Index: 911789 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.9167. Min Act: -0.1700
Data Index: 710097 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.8691. Min Act: -0.1700
Data Index: 146560 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.8850. Min Act: -0.1700
Data Index: 1045509 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.8691. Min Act: -0.1700
Data Index: 8893 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.8691. Min Act: -0.1700
Data Index: 547484 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.8532. Min Act: -0.1700
Data Index: 544489 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.8691. Min Act: -0.1700
Data Index: 666049 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.8532. Min Act: -0.1700
Data Index: 956945 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.8850. Min Act: -0.1700
Data Index: 975830 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.8532. Min Act: -0.1700
Data Index: 612087 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9800. Min Range: -2.9800
Max Act: 2.8055. Min Act: -0.1700
Data Index: 472241 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19