Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4572 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0476. Min Range: -7.0476
Max Act: 7.0476. Min Act: -0.1700
Data Index: 4162864 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0476. Min Range: -7.0476
Max Act: 7.0163. Min Act: -0.1700
Data Index: 3442769 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.8913. Min Act: -0.1700
Data Index: 5926838 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.8601. Min Act: -0.1700
Data Index: 3169969 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.7976. Min Act: -0.1700
Data Index: 7211645 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.7038. Min Act: -0.1700
Data Index: 3684744 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.6726. Min Act: -0.1700
Data Index: 2924388 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.7038. Min Act: -0.1700
Data Index: 202286 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.6726. Min Act: -0.1700
Data Index: 288773 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.6413. Min Act: -0.1700
Data Index: 6408580 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.6413. Min Act: -0.1700
Data Index: 4117071 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.6101. Min Act: -0.1700
Data Index: 6046202 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.6413. Min Act: -0.1700
Data Index: 3078703 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.5476. Min Act: -0.1700
Data Index: 4669149 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.5476. Min Act: -0.1700
Data Index: 8050815 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.5476. Min Act: -0.1700
Data Index: 5939824 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.6101. Min Act: -0.1700
Data Index: 4430418 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.5476. Min Act: -0.1700
Data Index: 2915898 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.5476. Min Act: -0.1700
Data Index: 2198535 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0476. Min Range: -7.0476
Max Act: 6.5163. Min Act: -0.1700
Data Index: 1827032 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19