Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3234 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.6078. Min Act: -0.1700
Data Index: 4114412 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.4828. Min Act: -0.1700
Data Index: 6808189 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.3890. Min Act: -0.1700
Data Index: 261390 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.3890. Min Act: -0.1700
Data Index: 8058126 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.3578. Min Act: -0.1700
Data Index: 3232031 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.3578. Min Act: -0.1700
Data Index: 4374519 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.3265. Min Act: -0.1700
Data Index: 2774552 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.3265. Min Act: -0.1700
Data Index: 6577442 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.2953. Min Act: -0.1700
Data Index: 6549168 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.2953. Min Act: -0.1700
Data Index: 2163855 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.2328. Min Act: -0.1700
Data Index: 3238239 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.2015. Min Act: -0.1700
Data Index: 7674616 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.1703. Min Act: -0.1700
Data Index: 1502827 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.1390. Min Act: -0.1700
Data Index: 8551628 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.1390. Min Act: -0.1700
Data Index: 7658312 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.1390. Min Act: -0.1700
Data Index: 5049342 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.1390. Min Act: -0.1700
Data Index: 4523949 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.1390. Min Act: -0.1700
Data Index: 4608384 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.0765. Min Act: -0.1700
Data Index: 6897343 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6078. Min Range: -6.6078
Max Act: 6.0765. Min Act: -0.1700
Data Index: 8063512 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19