Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3749. Min Act: -0.1700
Data Index: 5962669 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3749. Min Act: -0.1700
Data Index: 2062944 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3749. Min Act: -0.1700
Data Index: 8638596 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3749. Min Act: -0.1700
Data Index: 550642 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3435. Min Act: -0.1700
Data Index: 4528553 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3435. Min Act: -0.1700
Data Index: 6188548 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3435. Min Act: -0.1700
Data Index: 2593533 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3435. Min Act: -0.1700
Data Index: 3003760 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3435. Min Act: -0.1700
Data Index: 6572963 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3435. Min Act: -0.1700
Data Index: 1648876 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3435. Min Act: -0.1700
Data Index: 5740826 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3122. Min Act: -0.1700
Data Index: 7132654 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3122. Min Act: -0.1700
Data Index: 5908409 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3122. Min Act: -0.1700
Data Index: 1322114 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3122. Min Act: -0.1700
Data Index: 445288 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3122. Min Act: -0.1700
Data Index: 3324822 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3122. Min Act: -0.1700
Data Index: 2824931 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3122. Min Act: -0.1700
Data Index: 108453 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.3122. Min Act: -0.1700
Data Index: 5961968 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3749. Min Range: -3.3749
Max Act: 3.2808. Min Act: -0.1700
Data Index: 3575148 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19