Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1955 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.4873. Min Act: -0.1700
Data Index: 8614813 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.4873. Min Act: -0.1700
Data Index: 3649083 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.4561. Min Act: -0.1700
Data Index: 8500786 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.3623. Min Act: -0.1700
Data Index: 6479418 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.3311. Min Act: -0.1700
Data Index: 7962467 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.3311. Min Act: -0.1700
Data Index: 4974704 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.2998. Min Act: -0.1700
Data Index: 2237499 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.2998. Min Act: -0.1700
Data Index: 7926557 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.2061. Min Act: -0.1700
Data Index: 3788799 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.2061. Min Act: -0.1700
Data Index: 2698296 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.2061. Min Act: -0.1700
Data Index: 5870777 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.1748. Min Act: -0.1700
Data Index: 4136764 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.1436. Min Act: -0.1700
Data Index: 7965983 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.1436. Min Act: -0.1700
Data Index: 1577238 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.1123. Min Act: -0.1700
Data Index: 1358202 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.0811. Min Act: -0.1700
Data Index: 3808235 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.0498. Min Act: -0.1700
Data Index: 4624513 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.0186. Min Act: -0.1700
Data Index: 6948584 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.0186. Min Act: -0.1700
Data Index: 411695 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4873. Min Range: -6.4873
Max Act: 6.0186. Min Act: -0.1700
Data Index: 7965984 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19