Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4406 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4954. Min Range: -8.4954
Max Act: 8.4954. Min Act: -0.1700
Data Index: 2446340 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4954. Min Range: -8.4954
Max Act: 8.1516. Min Act: -0.1700
Data Index: 1199202 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4954. Min Range: -8.4954
Max Act: 8.1516. Min Act: -0.1700
Data Index: 2767357 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4954. Min Range: -8.4954
Max Act: 8.0579. Min Act: -0.1700
Data Index: 5896913 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4954. Min Range: -8.4954
Max Act: 8.0266. Min Act: -0.1700
Data Index: 677791 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4954. Min Range: -8.4954
Max Act: 8.0266. Min Act: -0.1700
Data Index: 2934062 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4954. Min Range: -8.4954
Max Act: 8.0579. Min Act: -0.1700
Data Index: 3540972 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4954. Min Range: -8.4954
Max Act: 7.9641. Min Act: -0.1700
Data Index: 7527056 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4954. Min Range: -8.4954
Max Act: 7.9329. Min Act: -0.1700
Data Index: 5815082 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4954. Min Range: -8.4954
Max Act: 7.9329. Min Act: -0.1700
Data Index: 611327 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4954. Min Range: -8.4954
Max Act: 7.8704. Min Act: -0.1700
Data Index: 8710349 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4954. Min Range: -8.4954
Max Act: 7.8704. Min Act: -0.1700
Data Index: 5194839 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4954. Min Range: -8.4954
Max Act: 7.8391. Min Act: -0.1700
Data Index: 6197926 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4954. Min Range: -8.4954
Max Act: 7.8391. Min Act: -0.1700
Data Index: 6733469 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4954. Min Range: -8.4954
Max Act: 7.8391. Min Act: -0.1700
Data Index: 1617957 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4954. Min Range: -8.4954
Max Act: 7.7454. Min Act: -0.1700
Data Index: 7261964 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4954. Min Range: -8.4954
Max Act: 7.7766. Min Act: -0.1700
Data Index: 4963941 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4954. Min Range: -8.4954
Max Act: 7.7454. Min Act: -0.1700
Data Index: 7975198 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4954. Min Range: -8.4954
Max Act: 7.7454. Min Act: -0.1700
Data Index: 5411015 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4954. Min Range: -8.4954
Max Act: 7.7141. Min Act: -0.1700
Data Index: 2359244 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19