Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0744. Min Range: -4.0744
Max Act: 4.0744. Min Act: -0.1700
Data Index: 1900679 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0744. Min Range: -4.0744
Max Act: 4.0432. Min Act: -0.1700
Data Index: 313502 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0744. Min Range: -4.0744
Max Act: 4.0432. Min Act: -0.1700
Data Index: 6416080 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0744. Min Range: -4.0744
Max Act: 4.0432. Min Act: -0.1700
Data Index: 6467764 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0744. Min Range: -4.0744
Max Act: 4.0432. Min Act: -0.1700
Data Index: 3290331 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0744. Min Range: -4.0744
Max Act: 4.0432. Min Act: -0.1700
Data Index: 865636 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0744. Min Range: -4.0744
Max Act: 4.0432. Min Act: -0.1700
Data Index: 6884435 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0744. Min Range: -4.0744
Max Act: 4.0119. Min Act: -0.1700
Data Index: 2532601 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0744. Min Range: -4.0744
Max Act: 4.0119. Min Act: -0.1700
Data Index: 4634102 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0744. Min Range: -4.0744
Max Act: 4.0119. Min Act: -0.1700
Data Index: 4575634 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0744. Min Range: -4.0744
Max Act: 4.0119. Min Act: -0.1700
Data Index: 8740379 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0744. Min Range: -4.0744
Max Act: 4.0119. Min Act: -0.1699
Data Index: 6905840 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0744. Min Range: -4.0744
Max Act: 4.0119. Min Act: -0.1700
Data Index: 2293413 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0744. Min Range: -4.0744
Max Act: 4.0119. Min Act: -0.1700
Data Index: 1788955 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0744. Min Range: -4.0744
Max Act: 4.0119. Min Act: -0.1700
Data Index: 56159 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0744. Min Range: -4.0744
Max Act: 3.9807. Min Act: -0.1700
Data Index: 5975011 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0744. Min Range: -4.0744
Max Act: 3.9807. Min Act: -0.1700
Data Index: 5464159 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0744. Min Range: -4.0744
Max Act: 3.9494. Min Act: -0.1700
Data Index: 3857429 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0744. Min Range: -4.0744
Max Act: 3.9807. Min Act: -0.1700
Data Index: 111760 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0744. Min Range: -4.0744
Max Act: 3.9807. Min Act: -0.1700
Data Index: 735131 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19