Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1782 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.6471. Min Act: -0.1700
Data Index: 672344 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5667. Min Act: -0.1700
Data Index: 705935 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5667. Min Act: -0.1700
Data Index: 185477 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5505. Min Act: -0.1700
Data Index: 178771 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5182. Min Act: -0.1700
Data Index: 552887 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5344. Min Act: -0.1700
Data Index: 871982 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5344. Min Act: -0.1700
Data Index: 1179317 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5182. Min Act: -0.1700
Data Index: 976838 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5182. Min Act: -0.1700
Data Index: 1223182 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5182. Min Act: -0.1700
Data Index: 779014 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5182. Min Act: -0.1700
Data Index: 804753 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5344. Min Act: -0.1700
Data Index: 905310 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5344. Min Act: -0.1699
Data Index: 969937 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5344. Min Act: -0.1700
Data Index: 603586 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5182. Min Act: -0.1700
Data Index: 1346210 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5182. Min Act: -0.1700
Data Index: 975488 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5020. Min Act: -0.1700
Data Index: 52562 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5020. Min Act: -0.1700
Data Index: 1096453 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5020. Min Act: -0.1700
Data Index: 165215 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6471. Min Range: -2.6471
Max Act: 2.5020. Min Act: -0.1700
Data Index: 625624 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19