Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1514 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.8523. Min Act: -0.1700
Data Index: 6544411 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.8211. Min Act: -0.1700
Data Index: 845700 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6961. Min Act: -0.1700
Data Index: 315168 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6961. Min Act: -0.1700
Data Index: 1771891 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6961. Min Act: -0.1700
Data Index: 205854 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6961. Min Act: -0.1693
Data Index: 8824395 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6648. Min Act: -0.1700
Data Index: 4762398 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6648. Min Act: -0.1700
Data Index: 5339663 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6648. Min Act: -0.1700
Data Index: 4682926 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6336. Min Act: -0.1700
Data Index: 701821 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6648. Min Act: -0.1700
Data Index: 8717505 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6648. Min Act: -0.1700
Data Index: 2658025 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6648. Min Act: -0.1700
Data Index: 7284132 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6336. Min Act: -0.1700
Data Index: 1165608 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6336. Min Act: -0.1700
Data Index: 3795141 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6336. Min Act: -0.1700
Data Index: 3983145 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6336. Min Act: -0.1700
Data Index: 3178331 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6336. Min Act: -0.1700
Data Index: 363741 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6023. Min Act: -0.1700
Data Index: 4331004 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8523. Min Range: -4.8523
Max Act: 4.6336. Min Act: -0.1700
Data Index: 2414339 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19