Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2000 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9091. Min Range: -6.9091
Max Act: 6.9091. Min Act: -0.1700
Data Index: 6513775 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9091. Min Range: -6.9091
Max Act: 6.3779. Min Act: -0.1700
Data Index: 5827974 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9091. Min Range: -6.9091
Max Act: 6.1904. Min Act: -0.1700
Data Index: 1041554 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9091. Min Range: -6.9091
Max Act: 6.1279. Min Act: -0.1700
Data Index: 7555105 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9091. Min Range: -6.9091
Max Act: 6.0654. Min Act: -0.1700
Data Index: 2214308 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9091. Min Range: -6.9091
Max Act: 6.0029. Min Act: -0.1700
Data Index: 1990129 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9091. Min Range: -6.9091
Max Act: 5.9716. Min Act: -0.1700
Data Index: 7660465 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9091. Min Range: -6.9091
Max Act: 5.9404. Min Act: -0.1700
Data Index: 5227155 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9091. Min Range: -6.9091
Max Act: 5.9404. Min Act: -0.1700
Data Index: 6763341 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9091. Min Range: -6.9091
Max Act: 5.9716. Min Act: -0.1700
Data Index: 2700213 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9091. Min Range: -6.9091
Max Act: 5.9404. Min Act: -0.1700
Data Index: 6879120 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9091. Min Range: -6.9091
Max Act: 5.9091. Min Act: -0.1700
Data Index: 7962987 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9091. Min Range: -6.9091
Max Act: 5.8466. Min Act: -0.1700
Data Index: 3462584 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9091. Min Range: -6.9091
Max Act: 5.8154. Min Act: -0.1700
Data Index: 918377 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9091. Min Range: -6.9091
Max Act: 5.7841. Min Act: -0.1700
Data Index: 7050978 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9091. Min Range: -6.9091
Max Act: 5.8154. Min Act: -0.1700
Data Index: 8480532 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9091. Min Range: -6.9091
Max Act: 5.8154. Min Act: -0.1700
Data Index: 8387374 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9091. Min Range: -6.9091
Max Act: 5.7841. Min Act: -0.1700
Data Index: 4675137 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9091. Min Range: -6.9091
Max Act: 5.7841. Min Act: -0.1700
Data Index: 7469208 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9091. Min Range: -6.9091
Max Act: 5.7841. Min Act: -0.1700
Data Index: 2781974 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19