Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4199 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.8267. Min Act: -0.1700
Data Index: 4746970 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.6704. Min Act: -0.1700
Data Index: 5824260 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.6392. Min Act: -0.1700
Data Index: 2328718 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.6392. Min Act: -0.1700
Data Index: 2298560 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.6392. Min Act: -0.1700
Data Index: 5210450 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.6392. Min Act: -0.1700
Data Index: 2124806 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.5767. Min Act: -0.1700
Data Index: 6964221 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.5767. Min Act: -0.1700
Data Index: 7748328 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.5142. Min Act: -0.1700
Data Index: 3636765 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.5454. Min Act: -0.1700
Data Index: 893220 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.5142. Min Act: -0.1700
Data Index: 5602455 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4829. Min Act: -0.1700
Data Index: 993234 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4829. Min Act: -0.1700
Data Index: 400860 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4829. Min Act: -0.1700
Data Index: 248709 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.5142. Min Act: -0.1700
Data Index: 5060505 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4829. Min Act: -0.1700
Data Index: 2110636 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4517. Min Act: -0.1700
Data Index: 2671990 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4517. Min Act: -0.1700
Data Index: 1718716 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4829. Min Act: -0.1700
Data Index: 433226 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4829. Min Act: -0.1700
Data Index: 3951861 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19