Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 991 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.7032. Min Act: -0.1700
Data Index: 4941819 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.6094. Min Act: -0.1700
Data Index: 7175863 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.5782. Min Act: -0.1700
Data Index: 6940173 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.5782. Min Act: -0.1700
Data Index: 3652583 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.5469. Min Act: -0.1700
Data Index: 1375500 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.5157. Min Act: -0.1700
Data Index: 8591195 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.4844. Min Act: -0.1700
Data Index: 7835567 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.4532. Min Act: -0.1700
Data Index: 6302919 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.4219. Min Act: -0.1700
Data Index: 5434489 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.4219. Min Act: -0.1700
Data Index: 3827344 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.4219. Min Act: -0.1700
Data Index: 2569574 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.4219. Min Act: -0.1700
Data Index: 6208567 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.3594. Min Act: -0.1700
Data Index: 8469430 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.3907. Min Act: -0.1700
Data Index: 966052 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.3907. Min Act: -0.1700
Data Index: 4127121 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.3594. Min Act: -0.1700
Data Index: 4251520 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.3282. Min Act: -0.1700
Data Index: 2211553 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.3282. Min Act: -0.1700
Data Index: 660296 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.3282. Min Act: -0.1700
Data Index: 2108903 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7032. Min Range: -5.7032
Max Act: 5.3282. Min Act: -0.1700
Data Index: 8304487 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19