Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1805 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.7516. Min Act: -0.1700
Data Index: 22949 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.7197. Min Act: -0.1700
Data Index: 951784 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.6877. Min Act: -0.1700
Data Index: 915896 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.6717. Min Act: -0.1700
Data Index: 1171816 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.6717. Min Act: -0.1700
Data Index: 419997 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.6556. Min Act: -0.1700
Data Index: 577864 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.6556. Min Act: -0.1700
Data Index: 723312 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.6396. Min Act: -0.1700
Data Index: 955673 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.6235. Min Act: -0.1700
Data Index: 585798 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.6074. Min Act: -0.1700
Data Index: 263712 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.6235. Min Act: -0.1700
Data Index: 615934 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.6074. Min Act: -0.1700
Data Index: 1359489 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.6396. Min Act: -0.1700
Data Index: 826292 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.6074. Min Act: -0.1700
Data Index: 495040 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.6074. Min Act: -0.1700
Data Index: 215535 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.6074. Min Act: -0.1700
Data Index: 1244198 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.6074. Min Act: -0.1700
Data Index: 1039599 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.6074. Min Act: -0.1700
Data Index: 1166529 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.5752. Min Act: -0.1700
Data Index: 1082330 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7516. Min Range: -2.7516
Max Act: 2.5914. Min Act: -0.1700
Data Index: 399049 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19