Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2002 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.5027. Min Act: -0.1700
Data Index: 12172 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.4865. Min Act: -0.1700
Data Index: 55812 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.4703. Min Act: -0.1700
Data Index: 898284 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.4540. Min Act: -0.1700
Data Index: 974104 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.4378. Min Act: -0.1700
Data Index: 773507 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.4215. Min Act: -0.1700
Data Index: 392406 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.4378. Min Act: -0.1700
Data Index: 1010640 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.4215. Min Act: -0.1700
Data Index: 776891 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.4052. Min Act: -0.1700
Data Index: 1140063 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.4052. Min Act: -0.1700
Data Index: 132252 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.4215. Min Act: -0.1700
Data Index: 776989 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.4215. Min Act: -0.1700
Data Index: 42915 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.3889. Min Act: -0.1700
Data Index: 679430 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.3725. Min Act: -0.1700
Data Index: 345141 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.3889. Min Act: -0.1700
Data Index: 1008323 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.3889. Min Act: -0.1700
Data Index: 795658 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.3725. Min Act: -0.1700
Data Index: 568844 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.3725. Min Act: -0.1700
Data Index: 902404 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.3889. Min Act: -0.1700
Data Index: 822368 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5027. Min Range: -2.5027
Max Act: 2.3889. Min Act: -0.1700
Data Index: 1350772 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19