Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4008 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1137. Min Range: -3.1137
Max Act: 3.1137. Min Act: -0.1700
Data Index: 6512004 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1137. Min Range: -3.1137
Max Act: 3.0033. Min Act: -0.1700
Data Index: 4487557 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.9716. Min Act: -0.1700
Data Index: 4083476 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.9083. Min Act: -0.1700
Data Index: 1974002 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.8924. Min Act: -0.1700
Data Index: 8709119 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.8766. Min Act: -0.1700
Data Index: 19015 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.8448. Min Act: -0.1700
Data Index: 4121874 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.8607. Min Act: -0.1700
Data Index: 2438916 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.8448. Min Act: -0.1700
Data Index: 5911896 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.8448. Min Act: -0.1700
Data Index: 4299344 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.8130. Min Act: -0.1700
Data Index: 7312367 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.7971. Min Act: -0.1700
Data Index: 2784505 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.7811. Min Act: -0.1700
Data Index: 1535687 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.7811. Min Act: -0.1700
Data Index: 165218 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.7971. Min Act: -0.1700
Data Index: 2112561 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.7811. Min Act: -0.1700
Data Index: 1497286 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.7811. Min Act: -0.1700
Data Index: 4450436 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.7811. Min Act: -0.1700
Data Index: 222762 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.7811. Min Act: -0.1700
Data Index: 1899363 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1137. Min Range: -3.1137
Max Act: 2.7811. Min Act: -0.1700
Data Index: 1271356 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19