Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 658 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.4818. Min Act: -0.1700
Data Index: 4586941 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.3881. Min Act: -0.1700
Data Index: 6402159 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.4193. Min Act: -0.1700
Data Index: 375147 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.3256. Min Act: -0.1700
Data Index: 7769596 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2631. Min Act: -0.1700
Data Index: 7242476 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.3256. Min Act: -0.1700
Data Index: 6273998 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2318. Min Act: -0.1700
Data Index: 7292512 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2006. Min Act: -0.1700
Data Index: 1163528 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2006. Min Act: -0.1700
Data Index: 7030972 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2006. Min Act: -0.1700
Data Index: 5691194 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.2318. Min Act: -0.1700
Data Index: 8820518 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1693. Min Act: -0.1700
Data Index: 3505143 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1693. Min Act: -0.1700
Data Index: 5002801 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1381. Min Act: -0.1700
Data Index: 4281985 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1381. Min Act: -0.1700
Data Index: 7829338 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.0756. Min Act: -0.1700
Data Index: 3091287 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.0756. Min Act: -0.1700
Data Index: 848222 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.1068. Min Act: -0.1700
Data Index: 593367 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.0756. Min Act: -0.1700
Data Index: 6853747 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4818. Min Range: -6.4818
Max Act: 6.0756. Min Act: -0.1700
Data Index: 5885401 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19