Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1281 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.1683. Min Range: -4.1683
Max Act: 4.1683. Min Act: -0.1700
Data Index: 730285 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1683. Min Range: -4.1683
Max Act: 4.1058. Min Act: -0.1700
Data Index: 1235068 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1683. Min Range: -4.1683
Max Act: 4.0745. Min Act: -0.1700
Data Index: 392418 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1683. Min Range: -4.1683
Max Act: 3.9651. Min Act: -0.1700
Data Index: 648498 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1683. Min Range: -4.1683
Max Act: 3.9807. Min Act: -0.1700
Data Index: 529954 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1683. Min Range: -4.1683
Max Act: 3.9963. Min Act: -0.1700
Data Index: 1093667 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1683. Min Range: -4.1683
Max Act: 3.9651. Min Act: -0.1700
Data Index: 1270142 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1683. Min Range: -4.1683
Max Act: 3.9807. Min Act: -0.1700
Data Index: 1132654 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1683. Min Range: -4.1683
Max Act: 3.9338. Min Act: -0.1700
Data Index: 366849 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1683. Min Range: -4.1683
Max Act: 3.9182. Min Act: -0.1700
Data Index: 414532 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1683. Min Range: -4.1683
Max Act: 3.9025. Min Act: -0.1698
Data Index: 78734 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1683. Min Range: -4.1683
Max Act: 3.9025. Min Act: -0.1700
Data Index: 930157 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1683. Min Range: -4.1683
Max Act: 3.9025. Min Act: -0.1700
Data Index: 1070376 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1683. Min Range: -4.1683
Max Act: 3.8713. Min Act: -0.1700
Data Index: 10860 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1683. Min Range: -4.1683
Max Act: 3.8713. Min Act: -0.1700
Data Index: 328212 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1683. Min Range: -4.1683
Max Act: 3.8869. Min Act: -0.1700
Data Index: 26022 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1683. Min Range: -4.1683
Max Act: 3.8713. Min Act: -0.1700
Data Index: 1248440 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1683. Min Range: -4.1683
Max Act: 3.8713. Min Act: -0.1700
Data Index: 272051 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1683. Min Range: -4.1683
Max Act: 3.8869. Min Act: -0.1700
Data Index: 1057212 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1683. Min Range: -4.1683
Max Act: 3.8556. Min Act: -0.1700
Data Index: 158422 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19