Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2185 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.4999. Min Act: -0.1700
Data Index: 7308242 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.4295. Min Act: -0.1700
Data Index: 4579000 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.4119. Min Act: -0.1700
Data Index: 8655793 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.4119. Min Act: -0.1700
Data Index: 1870767 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.4119. Min Act: -0.1700
Data Index: 5917484 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.3943. Min Act: -0.1700
Data Index: 5348125 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.3943. Min Act: -0.1700
Data Index: 3240121 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.3943. Min Act: -0.1700
Data Index: 7740926 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.3767. Min Act: -0.1700
Data Index: 3644319 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.3767. Min Act: -0.1700
Data Index: 8619286 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.3767. Min Act: -0.1700
Data Index: 7894840 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.3767. Min Act: -0.1700
Data Index: 7861586 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.3590. Min Act: -0.1700
Data Index: 4540961 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.3590. Min Act: -0.1700
Data Index: 139093 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.3590. Min Act: -0.1700
Data Index: 1505143 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.3590. Min Act: -0.1700
Data Index: 7342564 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.3590. Min Act: -0.1700
Data Index: 8568896 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.3414. Min Act: -0.1700
Data Index: 4210178 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.3414. Min Act: -0.1700
Data Index: 859568 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4999. Min Range: -1.4999
Max Act: 1.3414. Min Act: -0.1700
Data Index: 5624170 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19