Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3281 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.2929. Min Act: -0.1700
Data Index: 4538718 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.1992. Min Act: -0.1700
Data Index: 2974074 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.1054. Min Act: -0.1700
Data Index: 7332068 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.0429. Min Act: -0.1700
Data Index: 586807 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2929. Min Range: -4.2929
Max Act: 4.0116. Min Act: -0.1700
Data Index: 2982887 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2929. Min Range: -4.2929
Max Act: 3.9804. Min Act: -0.1700
Data Index: 7046363 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2929. Min Range: -4.2929
Max Act: 3.9804. Min Act: -0.1700
Data Index: 6732162 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2929. Min Range: -4.2929
Max Act: 3.9178. Min Act: -0.1700
Data Index: 5588843 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2929. Min Range: -4.2929
Max Act: 3.9491. Min Act: -0.1700
Data Index: 5331689 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2929. Min Range: -4.2929
Max Act: 3.9491. Min Act: -0.1700
Data Index: 1547091 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2929. Min Range: -4.2929
Max Act: 3.9491. Min Act: -0.1700
Data Index: 7729626 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2929. Min Range: -4.2929
Max Act: 3.9491. Min Act: -0.1700
Data Index: 1341794 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2929. Min Range: -4.2929
Max Act: 3.9491. Min Act: -0.1700
Data Index: 3645039 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2929. Min Range: -4.2929
Max Act: 3.9491. Min Act: -0.1700
Data Index: 1264565 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2929. Min Range: -4.2929
Max Act: 3.9491. Min Act: -0.1700
Data Index: 7884678 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2929. Min Range: -4.2929
Max Act: 3.9178. Min Act: -0.1700
Data Index: 2751268 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2929. Min Range: -4.2929
Max Act: 3.9178. Min Act: -0.1700
Data Index: 4862050 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2929. Min Range: -4.2929
Max Act: 3.9491. Min Act: -0.1700
Data Index: 3282048 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2929. Min Range: -4.2929
Max Act: 3.9178. Min Act: -0.1700
Data Index: 4291849 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2929. Min Range: -4.2929
Max Act: 3.9178. Min Act: -0.1700
Data Index: 6309157 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19