Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2970 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.2687. Min Act: -0.1700
Data Index: 7572722 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.2374. Min Act: -0.1700
Data Index: 7523846 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.2062. Min Act: -0.1700
Data Index: 6541071 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.2062. Min Act: -0.1700
Data Index: 745761 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.1749. Min Act: -0.1700
Data Index: 7325087 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.1749. Min Act: -0.1700
Data Index: 5511595 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.1437. Min Act: -0.1700
Data Index: 8559015 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.1749. Min Act: -0.1700
Data Index: 2106567 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.2062. Min Act: -0.1700
Data Index: 5672615 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.1437. Min Act: -0.1700
Data Index: 6541069 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.1437. Min Act: -0.1700
Data Index: 147487 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.1437. Min Act: -0.1700
Data Index: 3479547 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.1124. Min Act: -0.1700
Data Index: 3401220 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.1124. Min Act: -0.1700
Data Index: 7523845 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.1124. Min Act: -0.1700
Data Index: 1761588 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.1124. Min Act: -0.1700
Data Index: 4391622 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.1124. Min Act: -0.1700
Data Index: 147473 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.1124. Min Act: -0.1700
Data Index: 5327005 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.1124. Min Act: -0.1700
Data Index: 745749 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2687. Min Range: -6.2687
Max Act: 6.0812. Min Act: -0.1700
Data Index: 5327001 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19