Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4079 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2287. Min Range: -4.2287
Max Act: 4.2287. Min Act: -0.1700
Data Index: 5212060 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2287. Min Range: -4.2287
Max Act: 4.1349. Min Act: -0.1700
Data Index: 1428848 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2287. Min Range: -4.2287
Max Act: 4.1037. Min Act: -0.1700
Data Index: 6441447 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2287. Min Range: -4.2287
Max Act: 4.0724. Min Act: -0.1700
Data Index: 4372651 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2287. Min Range: -4.2287
Max Act: 4.0412. Min Act: -0.1700
Data Index: 7019630 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2287. Min Range: -4.2287
Max Act: 4.0412. Min Act: -0.1700
Data Index: 8370786 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2287. Min Range: -4.2287
Max Act: 4.0099. Min Act: -0.1700
Data Index: 163578 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2287. Min Range: -4.2287
Max Act: 4.0099. Min Act: -0.1700
Data Index: 2685298 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2287. Min Range: -4.2287
Max Act: 4.0099. Min Act: -0.1700
Data Index: 4249495 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9786. Min Act: -0.1700
Data Index: 5245845 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9786. Min Act: -0.1700
Data Index: 6684150 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9786. Min Act: -0.1700
Data Index: 6312846 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9786. Min Act: -0.1700
Data Index: 5263879 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9786. Min Act: -0.1700
Data Index: 1200207 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9786. Min Act: -0.1700
Data Index: 6938695 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9474. Min Act: -0.1700
Data Index: 8087227 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9474. Min Act: -0.1700
Data Index: 599385 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9474. Min Act: -0.1700
Data Index: 8113706 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9474. Min Act: -0.1700
Data Index: 5034085 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2287. Min Range: -4.2287
Max Act: 3.9161. Min Act: -0.1700
Data Index: 6879708 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19