Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3622 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.6216. Min Act: -0.1700
Data Index: 3202336 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.4966. Min Act: -0.1700
Data Index: 1235733 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.4653. Min Act: -0.1700
Data Index: 7737323 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.4653. Min Act: -0.1700
Data Index: 1549836 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.4028. Min Act: -0.1700
Data Index: 5137351 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.4028. Min Act: -0.1700
Data Index: 7539939 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.3716. Min Act: -0.1700
Data Index: 3419714 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.3403. Min Act: -0.1700
Data Index: 3966051 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.3091. Min Act: -0.1700
Data Index: 6564126 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.2778. Min Act: -0.1700
Data Index: 1070767 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.2778. Min Act: -0.1700
Data Index: 3449831 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.2778. Min Act: -0.1700
Data Index: 8382036 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.2466. Min Act: -0.1700
Data Index: 5609522 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.2153. Min Act: -0.1700
Data Index: 2394416 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.2153. Min Act: -0.1700
Data Index: 1727847 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.1841. Min Act: -0.1700
Data Index: 1035861 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.2153. Min Act: -0.1700
Data Index: 2622759 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.2153. Min Act: -0.1700
Data Index: 335507 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.2153. Min Act: -0.1700
Data Index: 1765797 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6216. Min Range: -6.6216
Max Act: 6.2153. Min Act: -0.1700
Data Index: 5266214 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19