Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 705 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 5.2009. Min Range: -5.2009
Max Act: 5.1696. Min Act: -0.1700
Data Index: 205744 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2009. Min Range: -5.2009
Max Act: 5.2009. Min Act: -0.1700
Data Index: 976090 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2009. Min Range: -5.2009
Max Act: 5.0759. Min Act: -0.1700
Data Index: 1006454 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2009. Min Range: -5.2009
Max Act: 5.0446. Min Act: -0.1700
Data Index: 1293802 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2009. Min Range: -5.2009
Max Act: 5.1071. Min Act: -0.1700
Data Index: 1234979 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2009. Min Range: -5.2009
Max Act: 5.1071. Min Act: -0.1700
Data Index: 391564 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2009. Min Range: -5.2009
Max Act: 5.0134. Min Act: -0.1700
Data Index: 823215 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2009. Min Range: -5.2009
Max Act: 5.0134. Min Act: -0.1700
Data Index: 931897 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2009. Min Range: -5.2009
Max Act: 4.9821. Min Act: -0.1700
Data Index: 1225748 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2009. Min Range: -5.2009
Max Act: 4.9821. Min Act: -0.1700
Data Index: 900891 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2009. Min Range: -5.2009
Max Act: 4.9821. Min Act: -0.1700
Data Index: 1280086 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2009. Min Range: -5.2009
Max Act: 4.9509. Min Act: -0.1700
Data Index: 112642 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2009. Min Range: -5.2009
Max Act: 4.9821. Min Act: -0.1700
Data Index: 655888 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2009. Min Range: -5.2009
Max Act: 4.9509. Min Act: -0.1700
Data Index: 401426 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2009. Min Range: -5.2009
Max Act: 4.9509. Min Act: -0.1700
Data Index: 341508 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2009. Min Range: -5.2009
Max Act: 4.9509. Min Act: -0.1700
Data Index: 776358 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2009. Min Range: -5.2009
Max Act: 4.9509. Min Act: -0.1700
Data Index: 1102000 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2009. Min Range: -5.2009
Max Act: 4.9509. Min Act: -0.1700
Data Index: 840817 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2009. Min Range: -5.2009
Max Act: 4.9196. Min Act: -0.1700
Data Index: 875956 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2009. Min Range: -5.2009
Max Act: 4.9196. Min Act: -0.1700
Data Index: 366426 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19