Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3407 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5302. Min Range: -6.5302
Max Act: 6.5302. Min Act: -0.1700
Data Index: 3137867 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5302. Min Range: -6.5302
Max Act: 6.3427. Min Act: -0.1700
Data Index: 3576202 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5302. Min Range: -6.5302
Max Act: 6.2490. Min Act: -0.1700
Data Index: 7731737 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5302. Min Range: -6.5302
Max Act: 6.2490. Min Act: -0.1700
Data Index: 7490577 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5302. Min Range: -6.5302
Max Act: 6.1865. Min Act: -0.1700
Data Index: 2860062 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5302. Min Range: -6.5302
Max Act: 6.1240. Min Act: -0.1700
Data Index: 5319644 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5302. Min Range: -6.5302
Max Act: 6.0615. Min Act: -0.1700
Data Index: 159625 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5302. Min Range: -6.5302
Max Act: 5.9990. Min Act: -0.1700
Data Index: 3219208 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5302. Min Range: -6.5302
Max Act: 5.9990. Min Act: -0.1700
Data Index: 7237406 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5302. Min Range: -6.5302
Max Act: 5.9677. Min Act: -0.1700
Data Index: 7908932 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5302. Min Range: -6.5302
Max Act: 5.9677. Min Act: -0.1700
Data Index: 7435962 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5302. Min Range: -6.5302
Max Act: 5.9677. Min Act: -0.1700
Data Index: 6795987 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5302. Min Range: -6.5302
Max Act: 5.9677. Min Act: -0.1700
Data Index: 36254 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5302. Min Range: -6.5302
Max Act: 5.9052. Min Act: -0.1700
Data Index: 8414738 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5302. Min Range: -6.5302
Max Act: 5.9365. Min Act: -0.1700
Data Index: 6651478 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5302. Min Range: -6.5302
Max Act: 5.9365. Min Act: -0.1700
Data Index: 4396522 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5302. Min Range: -6.5302
Max Act: 5.9052. Min Act: -0.1700
Data Index: 7117015 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5302. Min Range: -6.5302
Max Act: 5.9052. Min Act: -0.1700
Data Index: 5462370 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5302. Min Range: -6.5302
Max Act: 5.9365. Min Act: -0.1700
Data Index: 1391355 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5302. Min Range: -6.5302
Max Act: 5.8740. Min Act: -0.1700
Data Index: 3038552 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19