Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5106 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.8691. Min Act: -0.1700
Data Index: 6520556 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.8214. Min Act: -0.1700
Data Index: 8078579 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.8214. Min Act: -0.1700
Data Index: 6638001 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.8214. Min Act: -0.1700
Data Index: 6184177 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.7737. Min Act: -0.1700
Data Index: 4707140 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.7896. Min Act: -0.1700
Data Index: 2210434 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.7737. Min Act: -0.1700
Data Index: 3989222 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.7737. Min Act: -0.1700
Data Index: 7219538 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.7577. Min Act: -0.1700
Data Index: 2665102 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.7577. Min Act: -0.1700
Data Index: 5898658 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.7258. Min Act: -0.1700
Data Index: 4831867 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.7417. Min Act: -0.1700
Data Index: 3152501 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.7577. Min Act: -0.1700
Data Index: 321510 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.7258. Min Act: -0.1700
Data Index: 1425936 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.7258. Min Act: -0.1700
Data Index: 2646845 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.7258. Min Act: -0.1700
Data Index: 8034929 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.7258. Min Act: -0.1700
Data Index: 3398128 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.7258. Min Act: -0.1700
Data Index: 8731904 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.7258. Min Act: -0.1700
Data Index: 2736569 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8691. Min Range: -2.8691
Max Act: 2.7098. Min Act: -0.1700
Data Index: 329047 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19