Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2767 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.4775. Min Act: -0.1700
Data Index: 5907578 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.2900. Min Act: -0.1700
Data Index: 129143 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.2588. Min Act: -0.1700
Data Index: 4911790 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.2588. Min Act: -0.1700
Data Index: 1367519 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.2275. Min Act: -0.1700
Data Index: 7006210 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.2275. Min Act: -0.1700
Data Index: 2235793 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.1963. Min Act: -0.1700
Data Index: 25626 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.1963. Min Act: -0.1700
Data Index: 7066216 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.1650. Min Act: -0.1700
Data Index: 1003690 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.1338. Min Act: -0.1700
Data Index: 7531102 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.1338. Min Act: -0.1700
Data Index: 2024792 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.1025. Min Act: -0.1700
Data Index: 8010442 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.1025. Min Act: -0.1700
Data Index: 1516156 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.1025. Min Act: -0.1700
Data Index: 1762728 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.1338. Min Act: -0.1700
Data Index: 5054319 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.1025. Min Act: -0.1700
Data Index: 2706904 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.0713. Min Act: -0.1700
Data Index: 501705 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.0713. Min Act: -0.1700
Data Index: 1261264 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.0713. Min Act: -0.1700
Data Index: 6570342 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4775. Min Range: -6.4775
Max Act: 6.0713. Min Act: -0.1700
Data Index: 7024500 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19