Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3634 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5232. Min Range: -6.5232
Max Act: 6.5232. Min Act: -0.1700
Data Index: 2145856 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5232. Min Range: -6.5232
Max Act: 6.1795. Min Act: -0.1700
Data Index: 1557252 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5232. Min Range: -6.5232
Max Act: 6.0857. Min Act: -0.1700
Data Index: 5811481 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5232. Min Range: -6.5232
Max Act: 6.0857. Min Act: -0.1700
Data Index: 5811482 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5232. Min Range: -6.5232
Max Act: 5.8670. Min Act: -0.1700
Data Index: 32135 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5232. Min Range: -6.5232
Max Act: 5.8357. Min Act: -0.1700
Data Index: 6474612 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5232. Min Range: -6.5232
Max Act: 5.8357. Min Act: -0.1700
Data Index: 7006303 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5232. Min Range: -6.5232
Max Act: 5.8045. Min Act: -0.1700
Data Index: 563769 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5232. Min Range: -6.5232
Max Act: 5.8045. Min Act: -0.1700
Data Index: 2245908 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5232. Min Range: -6.5232
Max Act: 5.8045. Min Act: -0.1700
Data Index: 7970212 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5232. Min Range: -6.5232
Max Act: 5.8045. Min Act: -0.1700
Data Index: 3337546 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5232. Min Range: -6.5232
Max Act: 5.7420. Min Act: -0.1700
Data Index: 6918729 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5232. Min Range: -6.5232
Max Act: 5.7732. Min Act: -0.1700
Data Index: 452489 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5232. Min Range: -6.5232
Max Act: 5.7732. Min Act: -0.1700
Data Index: 3621265 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5232. Min Range: -6.5232
Max Act: 5.7420. Min Act: -0.1700
Data Index: 8100551 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5232. Min Range: -6.5232
Max Act: 5.7107. Min Act: -0.1700
Data Index: 5932491 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5232. Min Range: -6.5232
Max Act: 5.7107. Min Act: -0.1700
Data Index: 4861982 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5232. Min Range: -6.5232
Max Act: 5.6795. Min Act: -0.1700
Data Index: 6669226 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5232. Min Range: -6.5232
Max Act: 5.6795. Min Act: -0.1700
Data Index: 4331127 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5232. Min Range: -6.5232
Max Act: 5.6795. Min Act: -0.1700
Data Index: 5013807 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19