Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3079 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.7685. Min Act: -0.1700
Data Index: 4237948 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.7685. Min Act: -0.1700
Data Index: 1708426 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.7372. Min Act: -0.1700
Data Index: 6009686 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.7372. Min Act: -0.1700
Data Index: 7907968 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.7060. Min Act: -0.1700
Data Index: 5743801 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.7060. Min Act: -0.1700
Data Index: 7184233 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.7060. Min Act: -0.1700
Data Index: 1477224 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.7060. Min Act: -0.1700
Data Index: 3748251 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.6747. Min Act: -0.1700
Data Index: 2255112 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.6747. Min Act: -0.1700
Data Index: 2810213 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.6435. Min Act: -0.1700
Data Index: 1703009 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.6122. Min Act: -0.1700
Data Index: 2255125 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.6435. Min Act: -0.1700
Data Index: 2255113 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.6122. Min Act: -0.1700
Data Index: 7186931 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.6122. Min Act: -0.1700
Data Index: 6362727 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.5810. Min Act: -0.1700
Data Index: 1006077 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.6122. Min Act: -0.1700
Data Index: 2834533 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.6122. Min Act: -0.1700
Data Index: 6174989 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.6122. Min Act: -0.1700
Data Index: 7013506 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7685. Min Range: -5.7685
Max Act: 5.6122. Min Act: -0.1700
Data Index: 5250110 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19