Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3126 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.6833. Min Act: -0.1700
Data Index: 5654501 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.6520. Min Act: -0.1700
Data Index: 8434238 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.6208. Min Act: -0.1700
Data Index: 896651 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.5895. Min Act: -0.1700
Data Index: 1032287 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.5583. Min Act: -0.1700
Data Index: 3035324 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.5270. Min Act: -0.1700
Data Index: 6469238 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.5270. Min Act: -0.1700
Data Index: 5012756 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4958. Min Act: -0.1700
Data Index: 8799657 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4958. Min Act: -0.1700
Data Index: 8579192 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4645. Min Act: -0.1700
Data Index: 3849318 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4645. Min Act: -0.1700
Data Index: 2415130 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4333. Min Act: -0.1700
Data Index: 83206 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4645. Min Act: -0.1700
Data Index: 2056876 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4333. Min Act: -0.1700
Data Index: 1049422 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4333. Min Act: -0.1700
Data Index: 6940692 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4333. Min Act: -0.1700
Data Index: 5685674 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4020. Min Act: -0.1700
Data Index: 81591 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4020. Min Act: -0.1700
Data Index: 3387883 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4020. Min Act: -0.1700
Data Index: 5654502 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4020. Min Act: -0.1700
Data Index: 3832636 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19