Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2014 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.6284. Min Act: -0.1700
Data Index: 47765 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.5658. Min Act: -0.1700
Data Index: 1348646 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.5501. Min Act: -0.1700
Data Index: 805047 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.5344. Min Act: -0.1700
Data Index: 55411 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.5031. Min Act: -0.1700
Data Index: 87204 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.5031. Min Act: -0.1700
Data Index: 795294 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.5188. Min Act: -0.1700
Data Index: 322822 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.4561. Min Act: -0.1700
Data Index: 1023356 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.4718. Min Act: -0.1700
Data Index: 1150898 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.4874. Min Act: -0.1700
Data Index: 369917 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.4561. Min Act: -0.1700
Data Index: 593135 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.4561. Min Act: -0.1700
Data Index: 243556 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.4718. Min Act: -0.1700
Data Index: 1336357 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.4718. Min Act: -0.1700
Data Index: 996022 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.4561. Min Act: -0.1700
Data Index: 337958 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.4561. Min Act: -0.1700
Data Index: 626891 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.4561. Min Act: -0.1700
Data Index: 1161155 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.4561. Min Act: -0.1700
Data Index: 54857 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.4247. Min Act: -0.1700
Data Index: 1278885 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6284. Min Range: -3.6284
Max Act: 3.4091. Min Act: -0.1700
Data Index: 671277 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19