Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5944 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.6687. Min Act: -0.1700
Data Index: 6852466 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.4500. Min Act: -0.1700
Data Index: 8814166 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.4187. Min Act: -0.1700
Data Index: 560893 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.3562. Min Act: -0.1700
Data Index: 8312327 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.3562. Min Act: -0.1700
Data Index: 7727560 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.3250. Min Act: -0.1700
Data Index: 4668284 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.2937. Min Act: -0.1700
Data Index: 5871614 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.2937. Min Act: -0.1700
Data Index: 3211507 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.2937. Min Act: -0.1700
Data Index: 1154658 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.2937. Min Act: -0.1700
Data Index: 3175054 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.2000. Min Act: -0.1700
Data Index: 2282493 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.1687. Min Act: -0.1700
Data Index: 4240939 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.1687. Min Act: -0.1700
Data Index: 6922167 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.1687. Min Act: -0.1700
Data Index: 7634734 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.1062. Min Act: -0.1700
Data Index: 720843 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.1062. Min Act: -0.1700
Data Index: 5041587 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.0750. Min Act: -0.1700
Data Index: 6379430 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.0750. Min Act: -0.1700
Data Index: 305286 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.0437. Min Act: -0.1700
Data Index: 4022225 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6687. Min Range: -6.6687
Max Act: 6.0437. Min Act: -0.1700
Data Index: 6122004 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19