Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2011 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.6970. Min Act: -0.1700
Data Index: 5735698 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.6657. Min Act: -0.1700
Data Index: 7347513 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.6032. Min Act: -0.1700
Data Index: 1825782 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.5720. Min Act: -0.1700
Data Index: 1555977 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.5720. Min Act: -0.1700
Data Index: 7320902 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.5720. Min Act: -0.1700
Data Index: 1092505 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.5407. Min Act: -0.1700
Data Index: 6670866 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.5095. Min Act: -0.1700
Data Index: 6263671 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.5095. Min Act: -0.1700
Data Index: 6033906 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.4782. Min Act: -0.1700
Data Index: 7207990 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.5095. Min Act: -0.1700
Data Index: 387675 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.4782. Min Act: -0.1700
Data Index: 7976716 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.4470. Min Act: -0.1700
Data Index: 4111015 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.4782. Min Act: -0.1700
Data Index: 3366414 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.4782. Min Act: -0.1700
Data Index: 5489938 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.4157. Min Act: -0.1700
Data Index: 5447567 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.4470. Min Act: -0.1700
Data Index: 4523394 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.4470. Min Act: -0.1700
Data Index: 8110346 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.4470. Min Act: -0.1700
Data Index: 6928323 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6970. Min Range: -4.6970
Max Act: 4.4157. Min Act: -0.1700
Data Index: 6369210 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19