Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1779 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3226. Min Range: -6.3226
Max Act: 6.3226. Min Act: -0.1700
Data Index: 1427775 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3226. Min Range: -6.3226
Max Act: 6.0726. Min Act: -0.1700
Data Index: 7870906 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.9476. Min Act: -0.1700
Data Index: 4986309 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.8851. Min Act: -0.1700
Data Index: 2363647 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.8851. Min Act: -0.1700
Data Index: 3656580 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.8539. Min Act: -0.1700
Data Index: 7583589 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.7914. Min Act: -0.1700
Data Index: 1818216 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.7914. Min Act: -0.1700
Data Index: 7407572 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.7914. Min Act: -0.1700
Data Index: 7886774 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.7914. Min Act: -0.1700
Data Index: 7433771 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.7601. Min Act: -0.1700
Data Index: 6209929 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.7601. Min Act: -0.1700
Data Index: 1034658 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.7601. Min Act: -0.1700
Data Index: 3970328 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.7289. Min Act: -0.1700
Data Index: 4099745 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.6976. Min Act: -0.1700
Data Index: 2436717 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.6976. Min Act: -0.1700
Data Index: 8645182 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.6976. Min Act: -0.1700
Data Index: 2611156 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.6976. Min Act: -0.1700
Data Index: 2953011 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.6976. Min Act: -0.1700
Data Index: 7411174 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3226. Min Range: -6.3226
Max Act: 5.6664. Min Act: -0.1700
Data Index: 1652356 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19