Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3765 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0887. Min Range: -6.0887
Max Act: 6.0887. Min Act: -0.1700
Data Index: 5190325 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0887. Min Range: -6.0887
Max Act: 6.0262. Min Act: -0.1700
Data Index: 702047 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.9949. Min Act: -0.1700
Data Index: 8191462 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.9949. Min Act: -0.1700
Data Index: 5584186 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.9637. Min Act: -0.1700
Data Index: 3816630 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.9324. Min Act: -0.1700
Data Index: 625023 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.9012. Min Act: -0.1700
Data Index: 6236881 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.9012. Min Act: -0.1700
Data Index: 5649312 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.9012. Min Act: -0.1700
Data Index: 4951754 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.8699. Min Act: -0.1700
Data Index: 7430634 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.8699. Min Act: -0.1700
Data Index: 8405263 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.8387. Min Act: -0.1700
Data Index: 1160098 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.8387. Min Act: -0.1700
Data Index: 7399129 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.8387. Min Act: -0.1700
Data Index: 7222519 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.8387. Min Act: -0.1700
Data Index: 1247364 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.8387. Min Act: -0.1700
Data Index: 3450324 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.8074. Min Act: -0.1700
Data Index: 7458948 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.8074. Min Act: -0.1700
Data Index: 2807663 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.8074. Min Act: -0.1700
Data Index: 3181169 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0887. Min Range: -6.0887
Max Act: 5.7762. Min Act: -0.1700
Data Index: 3075335 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19