Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4625 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5206. Min Range: -5.5206
Max Act: 5.5206. Min Act: -0.1700
Data Index: 100616 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5206. Min Range: -5.5206
Max Act: 5.2706. Min Act: -0.1700
Data Index: 3861908 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5206. Min Range: -5.5206
Max Act: 5.0831. Min Act: -0.1700
Data Index: 8219186 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5206. Min Range: -5.5206
Max Act: 5.0831. Min Act: -0.1700
Data Index: 5438695 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5206. Min Range: -5.5206
Max Act: 5.0518. Min Act: -0.1700
Data Index: 4479770 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5206. Min Range: -5.5206
Max Act: 4.9893. Min Act: -0.1700
Data Index: 3620865 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5206. Min Range: -5.5206
Max Act: 4.9893. Min Act: -0.1700
Data Index: 7937573 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5206. Min Range: -5.5206
Max Act: 4.9893. Min Act: -0.1700
Data Index: 1172505 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5206. Min Range: -5.5206
Max Act: 4.9581. Min Act: -0.1700
Data Index: 749581 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5206. Min Range: -5.5206
Max Act: 4.9581. Min Act: -0.1700
Data Index: 4064048 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5206. Min Range: -5.5206
Max Act: 4.9268. Min Act: -0.1700
Data Index: 7419244 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5206. Min Range: -5.5206
Max Act: 4.9268. Min Act: -0.1700
Data Index: 7741543 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5206. Min Range: -5.5206
Max Act: 4.8956. Min Act: -0.1700
Data Index: 2256143 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5206. Min Range: -5.5206
Max Act: 4.8643. Min Act: -0.1700
Data Index: 2199873 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5206. Min Range: -5.5206
Max Act: 4.8956. Min Act: -0.1700
Data Index: 4820387 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5206. Min Range: -5.5206
Max Act: 4.8331. Min Act: -0.1700
Data Index: 312465 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5206. Min Range: -5.5206
Max Act: 4.8331. Min Act: -0.1700
Data Index: 2501165 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5206. Min Range: -5.5206
Max Act: 4.8331. Min Act: -0.1700
Data Index: 3673756 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5206. Min Range: -5.5206
Max Act: 4.8018. Min Act: -0.1700
Data Index: 5417518 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5206. Min Range: -5.5206
Max Act: 4.8018. Min Act: -0.1700
Data Index: 5665414 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19