Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3255 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.7927. Min Act: -0.1700
Data Index: 6031688 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.8239. Min Act: -0.1700
Data Index: 8143538 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.7927. Min Act: -0.1700
Data Index: 4373344 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.7614. Min Act: -0.1700
Data Index: 5030433 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.7614. Min Act: -0.1700
Data Index: 7314162 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.7302. Min Act: -0.1700
Data Index: 645386 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.6989. Min Act: -0.1700
Data Index: 960607 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.6989. Min Act: -0.1700
Data Index: 3092588 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.6677. Min Act: -0.1700
Data Index: 1012525 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.6989. Min Act: -0.1700
Data Index: 3255921 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.6677. Min Act: -0.1700
Data Index: 477259 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.6677. Min Act: -0.1700
Data Index: 6989488 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.6677. Min Act: -0.1700
Data Index: 3407441 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.6364. Min Act: -0.1700
Data Index: 26520 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.6364. Min Act: -0.1700
Data Index: 4661423 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.6364. Min Act: -0.1700
Data Index: 3040684 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.6677. Min Act: -0.1700
Data Index: 1415858 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.6364. Min Act: -0.1700
Data Index: 181130 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.6364. Min Act: -0.1700
Data Index: 6137910 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8239. Min Range: -5.8239
Max Act: 5.6364. Min Act: -0.1700
Data Index: 7762757 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19