Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4606 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4956. Min Range: -5.4956
Max Act: 5.4956. Min Act: -0.1700
Data Index: 4158800 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4956. Min Range: -5.4956
Max Act: 5.3706. Min Act: -0.1700
Data Index: 7303116 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4956. Min Range: -5.4956
Max Act: 5.1831. Min Act: -0.1700
Data Index: 6875695 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4956. Min Range: -5.4956
Max Act: 5.1206. Min Act: -0.1700
Data Index: 1417473 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4956. Min Range: -5.4956
Max Act: 5.0894. Min Act: -0.1700
Data Index: 8459605 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4956. Min Range: -5.4956
Max Act: 5.0894. Min Act: -0.1700
Data Index: 5351425 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4956. Min Range: -5.4956
Max Act: 5.0894. Min Act: -0.1700
Data Index: 2373106 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4956. Min Range: -5.4956
Max Act: 5.0581. Min Act: -0.1700
Data Index: 2002500 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4956. Min Range: -5.4956
Max Act: 5.0269. Min Act: -0.1700
Data Index: 6992856 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4956. Min Range: -5.4956
Max Act: 5.0269. Min Act: -0.1700
Data Index: 1349321 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4956. Min Range: -5.4956
Max Act: 5.0269. Min Act: -0.1700
Data Index: 2963501 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4956. Min Range: -5.4956
Max Act: 5.0269. Min Act: -0.1700
Data Index: 3063150 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4956. Min Range: -5.4956
Max Act: 5.0581. Min Act: -0.1700
Data Index: 7134773 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4956. Min Range: -5.4956
Max Act: 4.9956. Min Act: -0.1700
Data Index: 1365814 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4956. Min Range: -5.4956
Max Act: 4.9956. Min Act: -0.1700
Data Index: 1788625 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4956. Min Range: -5.4956
Max Act: 5.0269. Min Act: -0.1700
Data Index: 5443819 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4956. Min Range: -5.4956
Max Act: 4.9956. Min Act: -0.1700
Data Index: 4011649 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4956. Min Range: -5.4956
Max Act: 4.9331. Min Act: -0.1700
Data Index: 732426 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4956. Min Range: -5.4956
Max Act: 4.9644. Min Act: -0.1700
Data Index: 6531789 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4956. Min Range: -5.4956
Max Act: 4.9331. Min Act: -0.1700
Data Index: 3996367 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19