Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 47 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1922. Min Range: -6.1922
Max Act: 6.1609. Min Act: -0.1700
Data Index: 4608278 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1922. Min Range: -6.1922
Max Act: 6.1922. Min Act: -0.1700
Data Index: 1647407 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1922. Min Range: -6.1922
Max Act: 6.1609. Min Act: -0.1700
Data Index: 2704464 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1922. Min Range: -6.1922
Max Act: 6.1297. Min Act: -0.1700
Data Index: 7074299 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1922. Min Range: -6.1922
Max Act: 6.0984. Min Act: -0.1700
Data Index: 6456662 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1922. Min Range: -6.1922
Max Act: 6.0359. Min Act: -0.1700
Data Index: 3581509 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1922. Min Range: -6.1922
Max Act: 6.0047. Min Act: -0.1700
Data Index: 4677335 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1922. Min Range: -6.1922
Max Act: 6.0359. Min Act: -0.1700
Data Index: 1969925 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1922. Min Range: -6.1922
Max Act: 6.0047. Min Act: -0.1700
Data Index: 5206034 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1922. Min Range: -6.1922
Max Act: 6.0047. Min Act: -0.1700
Data Index: 3878039 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1922. Min Range: -6.1922
Max Act: 6.0047. Min Act: -0.1700
Data Index: 1347545 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1922. Min Range: -6.1922
Max Act: 6.0047. Min Act: -0.1700
Data Index: 4385138 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1922. Min Range: -6.1922
Max Act: 6.0047. Min Act: -0.1700
Data Index: 7381147 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1922. Min Range: -6.1922
Max Act: 5.9734. Min Act: -0.1700
Data Index: 7864424 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1922. Min Range: -6.1922
Max Act: 5.9422. Min Act: -0.1700
Data Index: 3958122 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1922. Min Range: -6.1922
Max Act: 5.9422. Min Act: -0.1700
Data Index: 43679 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1922. Min Range: -6.1922
Max Act: 5.9109. Min Act: -0.1700
Data Index: 3987521 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1922. Min Range: -6.1922
Max Act: 5.9109. Min Act: -0.1700
Data Index: 4456146 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1922. Min Range: -6.1922
Max Act: 5.9109. Min Act: -0.1700
Data Index: 2219494 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1922. Min Range: -6.1922
Max Act: 5.9109. Min Act: -0.1700
Data Index: 1109187 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19