Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1037 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.8879. Min Act: -0.1700
Data Index: 1174091 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.8879. Min Act: -0.1700
Data Index: 948911 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.8562. Min Act: -0.1700
Data Index: 1019041 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.8562. Min Act: -0.1700
Data Index: 41291 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.8562. Min Act: -0.1700
Data Index: 1264594 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.8244. Min Act: -0.1700
Data Index: 1381762 (Python Code)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.8244. Min Act: -0.1700
Data Index: 77888 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.8085. Min Act: -0.1700
Data Index: 355885 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.8085. Min Act: -0.1700
Data Index: 155636 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.8085. Min Act: -0.1700
Data Index: 339252 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.7925. Min Act: -0.1700
Data Index: 122788 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.7606. Min Act: -0.1700
Data Index: 1061283 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.7925. Min Act: -0.1700
Data Index: 1037783 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.7766. Min Act: -0.1700
Data Index: 954087 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.7447. Min Act: -0.1700
Data Index: 309894 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.7447. Min Act: -0.1700
Data Index: 208033 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.7447. Min Act: -0.1700
Data Index: 1080722 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.7606. Min Act: -0.1700
Data Index: 903546 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.7287. Min Act: -0.1700
Data Index: 1108642 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8879. Min Range: -2.8879
Max Act: 2.7127. Min Act: -0.1700
Data Index: 1087605 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19