Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2112 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.1404. Min Act: -0.1700
Data Index: 1324195 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.1404. Min Act: -0.1700
Data Index: 6052614 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.1404. Min Act: -0.1700
Data Index: 7863924 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.1404. Min Act: -0.1700
Data Index: 1833594 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.1404. Min Act: -0.1700
Data Index: 3245098 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.1089. Min Act: -0.1700
Data Index: 1406447 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.1089. Min Act: -0.1700
Data Index: 2127068 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.1089. Min Act: -0.1700
Data Index: 5289099 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.1089. Min Act: -0.1700
Data Index: 7615827 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.1089. Min Act: -0.1700
Data Index: 1015315 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.1404. Min Act: -0.1700
Data Index: 2715975 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.0931. Min Act: -0.1700
Data Index: 3534446 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.0931. Min Act: -0.1700
Data Index: 934549 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.0931. Min Act: -0.1700
Data Index: 8753953 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.0931. Min Act: -0.1700
Data Index: 1534132 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.0931. Min Act: -0.1700
Data Index: 6318515 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.0931. Min Act: -0.1700
Data Index: 845283 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.0931. Min Act: -0.1700
Data Index: 5536951 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.0774. Min Act: -0.1700
Data Index: 6661274 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1404. Min Range: -3.1404
Max Act: 3.0774. Min Act: -0.1700
Data Index: 4895270 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19