Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2504 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6787. Min Range: -7.6787
Max Act: 7.6787. Min Act: -0.1700
Data Index: 6704841 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6787. Min Range: -7.6787
Max Act: 7.1474. Min Act: -0.1700
Data Index: 2413686 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6787. Min Range: -7.6787
Max Act: 7.1162. Min Act: -0.1700
Data Index: 4814266 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6787. Min Range: -7.6787
Max Act: 7.0224. Min Act: -0.1700
Data Index: 8565792 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6787. Min Range: -7.6787
Max Act: 6.9287. Min Act: -0.1700
Data Index: 3952254 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6787. Min Range: -7.6787
Max Act: 6.8662. Min Act: -0.1700
Data Index: 2392733 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6787. Min Range: -7.6787
Max Act: 6.8662. Min Act: -0.1700
Data Index: 4865113 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6787. Min Range: -7.6787
Max Act: 6.8349. Min Act: -0.1700
Data Index: 7972176 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6787. Min Range: -7.6787
Max Act: 6.8349. Min Act: -0.1700
Data Index: 5780696 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6787. Min Range: -7.6787
Max Act: 6.7724. Min Act: -0.1700
Data Index: 321213 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6787. Min Range: -7.6787
Max Act: 6.8037. Min Act: -0.1700
Data Index: 1018839 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6787. Min Range: -7.6787
Max Act: 6.7724. Min Act: -0.1700
Data Index: 263956 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6787. Min Range: -7.6787
Max Act: 6.7099. Min Act: -0.1700
Data Index: 2132201 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6787. Min Range: -7.6787
Max Act: 6.7412. Min Act: -0.1700
Data Index: 7704525 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6787. Min Range: -7.6787
Max Act: 6.7412. Min Act: -0.1700
Data Index: 1841266 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6787. Min Range: -7.6787
Max Act: 6.7412. Min Act: -0.1700
Data Index: 2550155 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6787. Min Range: -7.6787
Max Act: 6.7412. Min Act: -0.1700
Data Index: 5038851 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6787. Min Range: -7.6787
Max Act: 6.7099. Min Act: -0.1700
Data Index: 7135933 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6787. Min Range: -7.6787
Max Act: 6.7099. Min Act: -0.1700
Data Index: 8676525 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6787. Min Range: -7.6787
Max Act: 6.6787. Min Act: -0.1700
Data Index: 3048750 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19