Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1799 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.3059. Min Act: -0.1700
Data Index: 3326455 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.2434. Min Act: -0.1700
Data Index: 2182065 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.1809. Min Act: -0.1700
Data Index: 7336323 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.1809. Min Act: -0.1700
Data Index: 1734457 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.1184. Min Act: -0.1700
Data Index: 512608 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.1184. Min Act: -0.1700
Data Index: 2778079 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.1184. Min Act: -0.1700
Data Index: 1413467 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.0871. Min Act: -0.1700
Data Index: 6966996 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.0559. Min Act: -0.1700
Data Index: 239914 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.0246. Min Act: -0.1700
Data Index: 2750862 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.0559. Min Act: -0.1700
Data Index: 6148722 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3059. Min Range: -5.3059
Max Act: 4.9934. Min Act: -0.1700
Data Index: 1608176 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.0246. Min Act: -0.1700
Data Index: 3340110 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.0246. Min Act: -0.1700
Data Index: 4593271 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.0246. Min Act: -0.1700
Data Index: 1101809 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.0246. Min Act: -0.1700
Data Index: 1710602 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.0246. Min Act: -0.1700
Data Index: 1450792 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.0559. Min Act: -0.1700
Data Index: 5398271 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.0246. Min Act: -0.1700
Data Index: 3023770 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3059. Min Range: -5.3059
Max Act: 5.0246. Min Act: -0.1700
Data Index: 506265 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19