Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4655 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.5970. Min Act: -0.1700
Data Index: 1727567 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.4408. Min Act: -0.1700
Data Index: 4375890 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.3470. Min Act: -0.1700
Data Index: 7655326 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.3158. Min Act: -0.1700
Data Index: 5785714 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.2533. Min Act: -0.1700
Data Index: 5016769 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.2533. Min Act: -0.1700
Data Index: 7407108 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.2220. Min Act: -0.1700
Data Index: 6117997 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.2220. Min Act: -0.1700
Data Index: 1739910 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.1908. Min Act: -0.1700
Data Index: 8645609 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.1908. Min Act: -0.1700
Data Index: 6793659 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.1595. Min Act: -0.1700
Data Index: 3249831 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.0658. Min Act: -0.1700
Data Index: 970690 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.0658. Min Act: -0.1700
Data Index: 4691764 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.0345. Min Act: -0.1700
Data Index: 3345994 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.0658. Min Act: -0.1700
Data Index: 272137 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.0345. Min Act: -0.1700
Data Index: 2639334 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.0033. Min Act: -0.1700
Data Index: 8663227 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5970. Min Range: -6.5970
Max Act: 6.0033. Min Act: -0.1700
Data Index: 3568313 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5970. Min Range: -6.5970
Max Act: 5.9720. Min Act: -0.1700
Data Index: 2986650 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5970. Min Range: -6.5970
Max Act: 5.9720. Min Act: -0.1700
Data Index: 7415528 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19