Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.2899. Min Act: -0.1700
Data Index: 580094 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.2899. Min Act: -0.1700
Data Index: 6295426 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.2586. Min Act: -0.1700
Data Index: 4747804 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.1336. Min Act: -0.1700
Data Index: 3258658 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.1336. Min Act: -0.1700
Data Index: 666840 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.1024. Min Act: -0.1700
Data Index: 2878869 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.1024. Min Act: -0.1700
Data Index: 6726438 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.1336. Min Act: -0.1700
Data Index: 4137012 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.1024. Min Act: -0.1700
Data Index: 905962 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.1336. Min Act: -0.1700
Data Index: 4578057 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.1024. Min Act: -0.1700
Data Index: 8293335 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.1024. Min Act: -0.1700
Data Index: 6240828 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.1024. Min Act: -0.1700
Data Index: 5880987 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.1024. Min Act: -0.1700
Data Index: 5824861 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.0711. Min Act: -0.1700
Data Index: 645153 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.0711. Min Act: -0.1700
Data Index: 6838046 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.0399. Min Act: -0.1700
Data Index: 2762580 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.1024. Min Act: -0.1700
Data Index: 7018326 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.0399. Min Act: -0.1700
Data Index: 3427875 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2899. Min Range: -5.2899
Max Act: 5.0711. Min Act: -0.1700
Data Index: 7216179 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19