Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2614 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2235. Min Range: -6.2235
Max Act: 6.2235. Min Act: -0.1700
Data Index: 3331627 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2235. Min Range: -6.2235
Max Act: 6.1298. Min Act: -0.1700
Data Index: 7031975 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2235. Min Range: -6.2235
Max Act: 6.0673. Min Act: -0.1700
Data Index: 1333096 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2235. Min Range: -6.2235
Max Act: 6.0985. Min Act: -0.1700
Data Index: 927185 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2235. Min Range: -6.2235
Max Act: 6.0048. Min Act: -0.1700
Data Index: 1587998 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2235. Min Range: -6.2235
Max Act: 6.0360. Min Act: -0.1700
Data Index: 5891121 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2235. Min Range: -6.2235
Max Act: 6.0048. Min Act: -0.1700
Data Index: 3722822 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2235. Min Range: -6.2235
Max Act: 5.9735. Min Act: -0.1700
Data Index: 7284868 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2235. Min Range: -6.2235
Max Act: 5.9735. Min Act: -0.1700
Data Index: 7408111 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2235. Min Range: -6.2235
Max Act: 5.9423. Min Act: -0.1700
Data Index: 2531762 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2235. Min Range: -6.2235
Max Act: 5.9423. Min Act: -0.1700
Data Index: 6154483 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2235. Min Range: -6.2235
Max Act: 5.8798. Min Act: -0.1700
Data Index: 8207666 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2235. Min Range: -6.2235
Max Act: 5.8798. Min Act: -0.1700
Data Index: 2294506 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2235. Min Range: -6.2235
Max Act: 5.8485. Min Act: -0.1700
Data Index: 2285242 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2235. Min Range: -6.2235
Max Act: 5.8485. Min Act: -0.1700
Data Index: 2796671 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2235. Min Range: -6.2235
Max Act: 5.8173. Min Act: -0.1700
Data Index: 1952734 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2235. Min Range: -6.2235
Max Act: 5.7860. Min Act: -0.1700
Data Index: 815348 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2235. Min Range: -6.2235
Max Act: 5.7860. Min Act: -0.1700
Data Index: 7136561 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2235. Min Range: -6.2235
Max Act: 5.7860. Min Act: -0.1700
Data Index: 7210567 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2235. Min Range: -6.2235
Max Act: 5.7860. Min Act: -0.1700
Data Index: 3290202 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19