Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 687 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0891. Min Range: -4.0891
Max Act: 4.0891. Min Act: -0.1700
Data Index: 539427 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0891. Min Range: -4.0891
Max Act: 4.0266. Min Act: -0.1700
Data Index: 1259022 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.9954. Min Act: -0.1700
Data Index: 1172053 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.9641. Min Act: -0.1700
Data Index: 97510 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.9641. Min Act: -0.1700
Data Index: 11808 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.9641. Min Act: -0.1700
Data Index: 879367 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.9015. Min Act: -0.1700
Data Index: 1238757 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.9015. Min Act: -0.1700
Data Index: 29694 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.9328. Min Act: -0.1700
Data Index: 868884 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.8859. Min Act: -0.1700
Data Index: 1218034 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.9172. Min Act: -0.1700
Data Index: 568233 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.8546. Min Act: -0.1700
Data Index: 704830 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.9172. Min Act: -0.1700
Data Index: 238044 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.8077. Min Act: -0.1700
Data Index: 1353358 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.8703. Min Act: -0.1700
Data Index: 1025879 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.8077. Min Act: -0.1700
Data Index: 265397 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.8546. Min Act: -0.1700
Data Index: 30579 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.8077. Min Act: -0.1700
Data Index: 1250599 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.7764. Min Act: -0.1700
Data Index: 474598 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0891. Min Range: -4.0891
Max Act: 3.8077. Min Act: -0.1700
Data Index: 1170322 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19