Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.6725. Min Act: -0.1700
Data Index: 3632925 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.7037. Min Act: -0.1700
Data Index: 1497873 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.6725. Min Act: -0.1700
Data Index: 896309 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.6725. Min Act: -0.1700
Data Index: 6212171 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.6412. Min Act: -0.1700
Data Index: 4607282 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.6100. Min Act: -0.1700
Data Index: 5173354 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.6412. Min Act: -0.1700
Data Index: 3191941 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.5787. Min Act: -0.1700
Data Index: 4457006 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.5162. Min Act: -0.1700
Data Index: 5424762 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.5162. Min Act: -0.1700
Data Index: 1289685 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.4850. Min Act: -0.1700
Data Index: 246621 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.4850. Min Act: -0.1700
Data Index: 8669577 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.4850. Min Act: -0.1700
Data Index: 6619505 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.4850. Min Act: -0.1700
Data Index: 2465679 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.4850. Min Act: -0.1700
Data Index: 730916 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.4850. Min Act: -0.1700
Data Index: 8360644 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.4850. Min Act: -0.1700
Data Index: 8651946 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.4850. Min Act: -0.1700
Data Index: 1362810 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.4850. Min Act: -0.1700
Data Index: 6623728 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7037. Min Range: -4.7037
Max Act: 4.4850. Min Act: -0.1700
Data Index: 1269358 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19