Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4727 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0844. Min Range: -4.0844
Max Act: 4.0844. Min Act: -0.1700
Data Index: 2582088 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0844. Min Range: -4.0844
Max Act: 4.0218. Min Act: -0.1700
Data Index: 2075971 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0844. Min Range: -4.0844
Max Act: 4.0218. Min Act: -0.1700
Data Index: 8520814 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0844. Min Range: -4.0844
Max Act: 4.0218. Min Act: -0.1700
Data Index: 644818 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0844. Min Range: -4.0844
Max Act: 4.0218. Min Act: -0.1700
Data Index: 406589 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0844. Min Range: -4.0844
Max Act: 3.9906. Min Act: -0.1700
Data Index: 6174232 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0844. Min Range: -4.0844
Max Act: 3.9906. Min Act: -0.1700
Data Index: 8618364 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0844. Min Range: -4.0844
Max Act: 3.9906. Min Act: -0.1700
Data Index: 2575828 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0844. Min Range: -4.0844
Max Act: 3.9906. Min Act: -0.1700
Data Index: 4678118 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0844. Min Range: -4.0844
Max Act: 3.9593. Min Act: -0.1700
Data Index: 3643116 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0844. Min Range: -4.0844
Max Act: 3.9593. Min Act: -0.1700
Data Index: 7873066 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0844. Min Range: -4.0844
Max Act: 3.9593. Min Act: -0.1700
Data Index: 5142550 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0844. Min Range: -4.0844
Max Act: 3.9593. Min Act: -0.1700
Data Index: 4008202 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0844. Min Range: -4.0844
Max Act: 3.9906. Min Act: -0.1700
Data Index: 1107788 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0844. Min Range: -4.0844
Max Act: 3.9593. Min Act: -0.1700
Data Index: 5947363 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0844. Min Range: -4.0844
Max Act: 3.9281. Min Act: -0.1700
Data Index: 5328395 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0844. Min Range: -4.0844
Max Act: 3.8968. Min Act: -0.1700
Data Index: 5797550 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0844. Min Range: -4.0844
Max Act: 3.8968. Min Act: -0.1700
Data Index: 5424123 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0844. Min Range: -4.0844
Max Act: 3.9281. Min Act: -0.1700
Data Index: 4045361 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0844. Min Range: -4.0844
Max Act: 3.8968. Min Act: -0.1700
Data Index: 4831083 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19