Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2992 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2318. Min Range: -7.2318
Max Act: 7.2318. Min Act: -0.1700
Data Index: 8125203 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2318. Min Range: -7.2318
Max Act: 7.2005. Min Act: -0.1700
Data Index: 8658833 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2318. Min Range: -7.2318
Max Act: 7.1693. Min Act: -0.1700
Data Index: 332172 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2318. Min Range: -7.2318
Max Act: 7.1380. Min Act: -0.1700
Data Index: 1720713 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2318. Min Range: -7.2318
Max Act: 7.1380. Min Act: -0.1700
Data Index: 700247 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2318. Min Range: -7.2318
Max Act: 7.0755. Min Act: -0.1700
Data Index: 5136245 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.9818. Min Act: -0.1700
Data Index: 7440977 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.9193. Min Act: -0.1700
Data Index: 3210857 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.9193. Min Act: -0.1700
Data Index: 7090233 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.8880. Min Act: -0.1700
Data Index: 1971466 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.8568. Min Act: -0.1700
Data Index: 7245132 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.8255. Min Act: -0.1700
Data Index: 3962952 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.7630. Min Act: -0.1700
Data Index: 7748107 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.7943. Min Act: -0.1700
Data Index: 2846662 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.7630. Min Act: -0.1700
Data Index: 6905828 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.7630. Min Act: -0.1700
Data Index: 3976030 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.7630. Min Act: -0.1700
Data Index: 7727650 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.7630. Min Act: -0.1700
Data Index: 3156534 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.7318. Min Act: -0.1700
Data Index: 5251808 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.7005. Min Act: -0.1700
Data Index: 5297652 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19