Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.9323. Min Act: -0.1700
Data Index: 2198254 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.8072. Min Act: -0.1700
Data Index: 2885278 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.5882. Min Act: -0.1700
Data Index: 5045641 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.5882. Min Act: -0.1700
Data Index: 2779789 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.5882. Min Act: -0.1700
Data Index: 6936326 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.5569. Min Act: -0.1700
Data Index: 2299503 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.5256. Min Act: -0.1700
Data Index: 3140290 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.5256. Min Act: -0.1700
Data Index: 5256000 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.5256. Min Act: -0.1700
Data Index: 5868027 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.5099. Min Act: -0.1700
Data Index: 457799 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.5099. Min Act: -0.1700
Data Index: 6840025 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.4629. Min Act: -0.1700
Data Index: 1505813 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.4786. Min Act: -0.1700
Data Index: 3296114 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.4942. Min Act: -0.1700
Data Index: 335777 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.4629. Min Act: -0.1700
Data Index: 7679534 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.4786. Min Act: -0.1700
Data Index: 8096503 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.4629. Min Act: -0.1700
Data Index: 2419818 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.4629. Min Act: -0.1700
Data Index: 812428 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.4472. Min Act: -0.1700
Data Index: 6820738 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9323. Min Range: -3.9323
Max Act: 3.4316. Min Act: -0.1700
Data Index: 1580739 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19