Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2437 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.9116. Min Act: -0.1700
Data Index: 1996425 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.8958. Min Act: -0.1700
Data Index: 805573 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.8322. Min Act: -0.1700
Data Index: 438719 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.8163. Min Act: -0.1700
Data Index: 1163158 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.8322. Min Act: -0.1700
Data Index: 5333648 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.7845. Min Act: -0.1700
Data Index: 6988780 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.7685. Min Act: -0.1700
Data Index: 7409391 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.7685. Min Act: -0.1700
Data Index: 5105447 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.7685. Min Act: -0.1700
Data Index: 8772909 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.7685. Min Act: -0.1700
Data Index: 3800092 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.7526. Min Act: -0.1700
Data Index: 3239435 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.7366. Min Act: -0.1700
Data Index: 785702 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.7206. Min Act: -0.1700
Data Index: 5529005 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.7206. Min Act: -0.1700
Data Index: 7465907 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.7206. Min Act: -0.1700
Data Index: 5284999 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.7366. Min Act: -0.1700
Data Index: 2800622 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.7366. Min Act: -0.1700
Data Index: 7703674 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.7047. Min Act: -0.1700
Data Index: 332006 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.7206. Min Act: -0.1700
Data Index: 6619908 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9116. Min Range: -2.9116
Max Act: 2.7047. Min Act: -0.1700
Data Index: 4381015 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19