Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3653 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3683. Min Range: -6.3683
Max Act: 6.3683. Min Act: -0.1700
Data Index: 2101831 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3683. Min Range: -6.3683
Max Act: 6.3370. Min Act: -0.1700
Data Index: 2459939 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3683. Min Range: -6.3683
Max Act: 6.3058. Min Act: -0.1700
Data Index: 929471 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3683. Min Range: -6.3683
Max Act: 6.2745. Min Act: -0.1700
Data Index: 2987355 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3683. Min Range: -6.3683
Max Act: 6.1183. Min Act: -0.1700
Data Index: 5622089 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3683. Min Range: -6.3683
Max Act: 6.0245. Min Act: -0.1700
Data Index: 4590663 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3683. Min Range: -6.3683
Max Act: 6.0245. Min Act: -0.1700
Data Index: 5117921 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3683. Min Range: -6.3683
Max Act: 6.0245. Min Act: -0.1700
Data Index: 6614046 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3683. Min Range: -6.3683
Max Act: 6.0245. Min Act: -0.1700
Data Index: 5170172 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3683. Min Range: -6.3683
Max Act: 5.9933. Min Act: -0.1700
Data Index: 6007417 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3683. Min Range: -6.3683
Max Act: 5.9933. Min Act: -0.1700
Data Index: 5247535 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3683. Min Range: -6.3683
Max Act: 5.9933. Min Act: -0.1700
Data Index: 4792793 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3683. Min Range: -6.3683
Max Act: 5.9933. Min Act: -0.1700
Data Index: 4712091 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3683. Min Range: -6.3683
Max Act: 5.9620. Min Act: -0.1700
Data Index: 8380590 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3683. Min Range: -6.3683
Max Act: 5.9620. Min Act: -0.1700
Data Index: 2736250 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3683. Min Range: -6.3683
Max Act: 5.8995. Min Act: -0.1700
Data Index: 7689675 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3683. Min Range: -6.3683
Max Act: 5.9308. Min Act: -0.1700
Data Index: 6591631 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3683. Min Range: -6.3683
Max Act: 5.8995. Min Act: -0.1700
Data Index: 1074358 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3683. Min Range: -6.3683
Max Act: 5.8995. Min Act: -0.1700
Data Index: 1122365 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3683. Min Range: -6.3683
Max Act: 5.8995. Min Act: -0.1700
Data Index: 3158921 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19