Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2054 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1509. Min Range: -5.1509
Max Act: 5.1509. Min Act: -0.1700
Data Index: 5054647 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1509. Min Range: -5.1509
Max Act: 5.0884. Min Act: -0.1700
Data Index: 616069 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1509. Min Range: -5.1509
Max Act: 5.0259. Min Act: -0.1700
Data Index: 5373447 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.9947. Min Act: -0.1700
Data Index: 6788609 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.9634. Min Act: -0.1700
Data Index: 4373180 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.9634. Min Act: -0.1700
Data Index: 6964800 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.9322. Min Act: -0.1700
Data Index: 6057649 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.9322. Min Act: -0.1700
Data Index: 3696769 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8697. Min Act: -0.1700
Data Index: 5588313 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8697. Min Act: -0.1700
Data Index: 7341946 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8697. Min Act: -0.1700
Data Index: 8705338 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8384. Min Act: -0.1700
Data Index: 238950 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8384. Min Act: -0.1700
Data Index: 1286785 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8384. Min Act: -0.1700
Data Index: 6427333 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8384. Min Act: -0.1700
Data Index: 4224574 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.8072. Min Act: -0.1700
Data Index: 123970 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.7759. Min Act: -0.1700
Data Index: 7814875 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.7759. Min Act: -0.1700
Data Index: 5413169 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.7759. Min Act: -0.1700
Data Index: 2412337 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1509. Min Range: -5.1509
Max Act: 4.7447. Min Act: -0.1700
Data Index: 238951 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19