Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2006 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.6944. Min Act: -0.1700
Data Index: 723258 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.6631. Min Act: -0.1700
Data Index: 356027 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.6631. Min Act: -0.1700
Data Index: 319376 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.6631. Min Act: -0.1700
Data Index: 289553 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.6631. Min Act: -0.1700
Data Index: 217095 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.6944. Min Act: -0.1700
Data Index: 216201 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.6944. Min Act: -0.1700
Data Index: 229988 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.5381. Min Act: -0.1700
Data Index: 134078 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.6631. Min Act: -0.1700
Data Index: 557347 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.6006. Min Act: -0.1700
Data Index: 1253153 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.5381. Min Act: -0.1700
Data Index: 93760 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.6006. Min Act: -0.1700
Data Index: 454652 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.5694. Min Act: -0.1700
Data Index: 915149 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.5694. Min Act: -0.1700
Data Index: 1175507 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.5381. Min Act: -0.1700
Data Index: 249205 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.5694. Min Act: -0.1700
Data Index: 1237879 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.5069. Min Act: -0.1700
Data Index: 940865 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.5381. Min Act: -0.1700
Data Index: 398097 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.4756. Min Act: -0.1700
Data Index: 467791 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6944. Min Range: -4.6944
Max Act: 4.4756. Min Act: -0.1700
Data Index: 1073423 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19