Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4130 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.9875. Min Act: -0.1700
Data Index: 3202023 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.9562. Min Act: -0.1700
Data Index: 3202027 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.9562. Min Act: -0.1700
Data Index: 5677057 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.8937. Min Act: -0.1700
Data Index: 3955451 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.8937. Min Act: -0.1700
Data Index: 6587693 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.8312. Min Act: -0.1700
Data Index: 8300254 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.8312. Min Act: -0.1700
Data Index: 8212905 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.7687. Min Act: -0.1700
Data Index: 2866736 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.8000. Min Act: -0.1700
Data Index: 8212903 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.7687. Min Act: -0.1700
Data Index: 7598553 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.7687. Min Act: -0.1700
Data Index: 8434020 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.7062. Min Act: -0.1700
Data Index: 604729 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.7062. Min Act: -0.1700
Data Index: 1524270 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.7062. Min Act: -0.1700
Data Index: 4138250 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.7062. Min Act: -0.1700
Data Index: 5767448 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.7062. Min Act: -0.1700
Data Index: 6057687 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.7062. Min Act: -0.1700
Data Index: 3115021 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.7062. Min Act: -0.1700
Data Index: 8249270 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.7062. Min Act: -0.1700
Data Index: 5567669 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9875. Min Range: -4.9875
Max Act: 4.7062. Min Act: -0.1700
Data Index: 362811 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19