Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5335 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.1785. Min Act: -0.1700
Data Index: 7001206 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0525. Min Act: -0.1700
Data Index: 8145777 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.9418. Min Act: -0.1700
Data Index: 2203930 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8943. Min Act: -0.1700
Data Index: 3860666 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8943. Min Act: -0.1700
Data Index: 2098711 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8784. Min Act: -0.1700
Data Index: 5736921 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8467. Min Act: -0.1700
Data Index: 5135054 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8467. Min Act: -0.1700
Data Index: 7556197 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8308. Min Act: -0.1700
Data Index: 4729743 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8308. Min Act: -0.1700
Data Index: 5217370 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8467. Min Act: -0.1700
Data Index: 6765052 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8308. Min Act: -0.1700
Data Index: 8512447 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8308. Min Act: -0.1700
Data Index: 2313189 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8149. Min Act: -0.1700
Data Index: 2385867 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.8149. Min Act: -0.1700
Data Index: 1981449 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.7989. Min Act: -0.1700
Data Index: 8315514 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.7989. Min Act: -0.1700
Data Index: 2172742 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.7830. Min Act: -0.1700
Data Index: 6181445 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.7830. Min Act: -0.1700
Data Index: 7222534 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1785. Min Range: -3.1785
Max Act: 2.7511. Min Act: -0.1700
Data Index: 2543584 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19