Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1271 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5954. Min Range: -8.5954
Max Act: 8.5954. Min Act: -0.1700
Data Index: 2653741 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5954. Min Range: -8.5954
Max Act: 8.4704. Min Act: -0.1700
Data Index: 5899781 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5954. Min Range: -8.5954
Max Act: 8.4079. Min Act: -0.1700
Data Index: 7752018 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5954. Min Range: -8.5954
Max Act: 8.3454. Min Act: -0.1700
Data Index: 7357517 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5954. Min Range: -8.5954
Max Act: 8.3454. Min Act: -0.1700
Data Index: 4731410 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5954. Min Range: -8.5954
Max Act: 8.2829. Min Act: -0.1700
Data Index: 2653742 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5954. Min Range: -8.5954
Max Act: 8.2204. Min Act: -0.1700
Data Index: 5204534 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5954. Min Range: -8.5954
Max Act: 8.0954. Min Act: -0.1700
Data Index: 5336534 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5954. Min Range: -8.5954
Max Act: 8.0329. Min Act: -0.1700
Data Index: 4581205 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5954. Min Range: -8.5954
Max Act: 8.0329. Min Act: -0.1700
Data Index: 3899507 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5954. Min Range: -8.5954
Max Act: 8.0329. Min Act: -0.1700
Data Index: 7559619 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5954. Min Range: -8.5954
Max Act: 7.9704. Min Act: -0.1700
Data Index: 2354617 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5954. Min Range: -8.5954
Max Act: 7.9704. Min Act: -0.1700
Data Index: 5055581 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5954. Min Range: -8.5954
Max Act: 7.9079. Min Act: -0.1700
Data Index: 1835779 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5954. Min Range: -8.5954
Max Act: 7.9079. Min Act: -0.1700
Data Index: 1878832 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5954. Min Range: -8.5954
Max Act: 7.9079. Min Act: -0.1700
Data Index: 1384934 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5954. Min Range: -8.5954
Max Act: 7.8454. Min Act: -0.1700
Data Index: 5234611 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5954. Min Range: -8.5954
Max Act: 7.8454. Min Act: -0.1700
Data Index: 1660632 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5954. Min Range: -8.5954
Max Act: 7.8454. Min Act: -0.1700
Data Index: 3994366 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5954. Min Range: -8.5954
Max Act: 7.8454. Min Act: -0.1700
Data Index: 4167062 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19