Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2467 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.7767. Min Act: -0.1700
Data Index: 870220 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.7141. Min Act: -0.1700
Data Index: 1854485 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.7141. Min Act: -0.1696
Data Index: 1887802 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6516. Min Act: -0.1700
Data Index: 8208019 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6516. Min Act: -0.1700
Data Index: 7552625 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6516. Min Act: -0.1700
Data Index: 2273135 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6516. Min Act: -0.1699
Data Index: 4514245 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6516. Min Act: -0.1700
Data Index: 3984757 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6203. Min Act: -0.1700
Data Index: 1417801 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.6203. Min Act: -0.1700
Data Index: 5899215 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5890. Min Act: -0.1700
Data Index: 2928944 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5890. Min Act: -0.1700
Data Index: 5106159 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5577. Min Act: -0.1700
Data Index: 13032 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5263. Min Act: -0.1700
Data Index: 5440129 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5263. Min Act: -0.1700
Data Index: 3965212 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5263. Min Act: -0.1700
Data Index: 1833616 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5263. Min Act: -0.1700
Data Index: 5300543 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5263. Min Act: -0.1700
Data Index: 734798 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5577. Min Act: -0.1700
Data Index: 682669 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7767. Min Range: -3.7767
Max Act: 3.5263. Min Act: -0.1700
Data Index: 5014889 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19