Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1973 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0925. Min Act: -0.1700
Data Index: 2544679 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0925. Min Act: -0.1700
Data Index: 3734417 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0612. Min Act: -0.1700
Data Index: 1668420 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0612. Min Act: -0.1700
Data Index: 2377002 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0612. Min Act: -0.1700
Data Index: 4690254 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0612. Min Act: -0.1700
Data Index: 1297484 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0612. Min Act: -0.1700
Data Index: 7415274 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0300. Min Act: -0.1700
Data Index: 3721080 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0300. Min Act: -0.1700
Data Index: 5424560 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0300. Min Act: -0.1700
Data Index: 2440568 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0300. Min Act: -0.1700
Data Index: 5189112 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0300. Min Act: -0.1700
Data Index: 4418841 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0300. Min Act: -0.1700
Data Index: 1380120 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0300. Min Act: -0.1700
Data Index: 3451171 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0300. Min Act: -0.1700
Data Index: 1893343 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0300. Min Act: -0.1700
Data Index: 3445701 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0300. Min Act: -0.1700
Data Index: 249661 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0300. Min Act: -0.1700
Data Index: 2811487 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0300. Min Act: -0.1700
Data Index: 2651692 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0925. Min Range: -4.0925
Max Act: 4.0300. Min Act: -0.1700
Data Index: 954924 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19