Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5470 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3096. Min Range: -7.3096
Max Act: 7.3096. Min Act: -0.1700
Data Index: 4080285 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.9971. Min Act: -0.1700
Data Index: 4550921 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.8721. Min Act: -0.1700
Data Index: 6410754 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.8408. Min Act: -0.1700
Data Index: 8190194 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.6846. Min Act: -0.1700
Data Index: 4375588 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.6533. Min Act: -0.1700
Data Index: 2724246 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.6221. Min Act: -0.1700
Data Index: 7177813 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.6221. Min Act: -0.1700
Data Index: 5532470 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.6221. Min Act: -0.1700
Data Index: 1851606 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.6221. Min Act: -0.1700
Data Index: 140029 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.5283. Min Act: -0.1700
Data Index: 1851605 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.4971. Min Act: -0.1700
Data Index: 5422957 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.5283. Min Act: -0.1700
Data Index: 4277538 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.4971. Min Act: -0.1700
Data Index: 8279445 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.4658. Min Act: -0.1700
Data Index: 3010252 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.4346. Min Act: -0.1700
Data Index: 7043848 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.4346. Min Act: -0.1700
Data Index: 2275377 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.4346. Min Act: -0.1700
Data Index: 4375597 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.4346. Min Act: -0.1700
Data Index: 7212727 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3096. Min Range: -7.3096
Max Act: 6.4346. Min Act: -0.1700
Data Index: 48009 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19