Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5485 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3350. Min Range: -4.3350
Max Act: 4.3350. Min Act: -0.1700
Data Index: 1533085 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3350. Min Range: -4.3350
Max Act: 4.0850. Min Act: -0.1700
Data Index: 6323736 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3350. Min Range: -4.3350
Max Act: 4.1163. Min Act: -0.1700
Data Index: 4526597 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3350. Min Range: -4.3350
Max Act: 4.0537. Min Act: -0.1700
Data Index: 2839116 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3350. Min Range: -4.3350
Max Act: 4.0537. Min Act: -0.1700
Data Index: 6804999 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3350. Min Range: -4.3350
Max Act: 4.0225. Min Act: -0.1700
Data Index: 71338 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3350. Min Range: -4.3350
Max Act: 3.9912. Min Act: -0.1700
Data Index: 2414668 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3350. Min Range: -4.3350
Max Act: 4.0225. Min Act: -0.1700
Data Index: 1369194 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3350. Min Range: -4.3350
Max Act: 4.0225. Min Act: -0.1700
Data Index: 160705 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3350. Min Range: -4.3350
Max Act: 4.0225. Min Act: -0.1700
Data Index: 5402038 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3350. Min Range: -4.3350
Max Act: 3.9912. Min Act: -0.1700
Data Index: 6587003 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3350. Min Range: -4.3350
Max Act: 3.9912. Min Act: -0.1700
Data Index: 3446945 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3350. Min Range: -4.3350
Max Act: 3.9600. Min Act: -0.1700
Data Index: 1575385 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3350. Min Range: -4.3350
Max Act: 3.9600. Min Act: -0.1700
Data Index: 1202706 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3350. Min Range: -4.3350
Max Act: 3.9287. Min Act: -0.1700
Data Index: 936197 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3350. Min Range: -4.3350
Max Act: 3.9287. Min Act: -0.1700
Data Index: 1762817 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3350. Min Range: -4.3350
Max Act: 3.9287. Min Act: -0.1700
Data Index: 6837616 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3350. Min Range: -4.3350
Max Act: 3.9287. Min Act: -0.1700
Data Index: 1044289 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3350. Min Range: -4.3350
Max Act: 3.9600. Min Act: -0.1700
Data Index: 1142230 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3350. Min Range: -4.3350
Max Act: 3.9287. Min Act: -0.1700
Data Index: 5978410 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19