Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2052 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.9704. Min Act: -0.1700
Data Index: 8435803 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.9391. Min Act: -0.1700
Data Index: 4691494 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.9079. Min Act: -0.1700
Data Index: 992106 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.9079. Min Act: -0.1700
Data Index: 274106 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.8454. Min Act: -0.1700
Data Index: 7532241 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.8454. Min Act: -0.1700
Data Index: 1468047 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.8454. Min Act: -0.1700
Data Index: 7810523 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.8141. Min Act: -0.1700
Data Index: 2200043 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.8141. Min Act: -0.1700
Data Index: 2608408 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.8141. Min Act: -0.1700
Data Index: 2715911 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.7829. Min Act: -0.1700
Data Index: 6186160 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.7829. Min Act: -0.1700
Data Index: 1372883 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.7829. Min Act: -0.1700
Data Index: 5547730 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.7829. Min Act: -0.1700
Data Index: 4693933 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.7829. Min Act: -0.1700
Data Index: 8205754 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.7516. Min Act: -0.1700
Data Index: 1586620 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.7516. Min Act: -0.1700
Data Index: 5426879 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.7516. Min Act: -0.1700
Data Index: 5838189 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.7516. Min Act: -0.1700
Data Index: 619541 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9704. Min Range: -4.9704
Max Act: 4.7516. Min Act: -0.1700
Data Index: 5941240 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19