Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2447 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0921. Min Range: -6.0921
Max Act: 6.0921. Min Act: -0.1700
Data Index: 6790169 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.9671. Min Act: -0.1700
Data Index: 1262954 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.8109. Min Act: -0.1700
Data Index: 2472440 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.7171. Min Act: -0.1700
Data Index: 3921902 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.7171. Min Act: -0.1700
Data Index: 624910 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.6234. Min Act: -0.1700
Data Index: 466740 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.5921. Min Act: -0.1700
Data Index: 8370320 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.4984. Min Act: -0.1700
Data Index: 4622634 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.4984. Min Act: -0.1700
Data Index: 791253 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.4359. Min Act: -0.1700
Data Index: 135382 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.4671. Min Act: -0.1700
Data Index: 31234 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.4671. Min Act: -0.1700
Data Index: 8002860 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.4671. Min Act: -0.1700
Data Index: 2211577 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.4984. Min Act: -0.1700
Data Index: 554668 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.4671. Min Act: -0.1700
Data Index: 1735142 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.4359. Min Act: -0.1700
Data Index: 89596 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.4359. Min Act: -0.1700
Data Index: 5659907 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.4046. Min Act: -0.1700
Data Index: 5598847 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.3734. Min Act: -0.1700
Data Index: 3977896 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0921. Min Range: -6.0921
Max Act: 5.4046. Min Act: -0.1700
Data Index: 5584987 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19