Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1594 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.8862. Min Act: -0.1700
Data Index: 4941853 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.8237. Min Act: -0.1700
Data Index: 4313242 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.8080. Min Act: -0.1700
Data Index: 6631172 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.7611. Min Act: -0.1700
Data Index: 1126585 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.7299. Min Act: -0.1700
Data Index: 6819676 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.7299. Min Act: -0.1700
Data Index: 5724454 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.7142. Min Act: -0.1700
Data Index: 214064 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.7142. Min Act: -0.1700
Data Index: 450756 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.6986. Min Act: -0.1700
Data Index: 8138429 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.6986. Min Act: -0.1700
Data Index: 693505 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.6829. Min Act: -0.1700
Data Index: 4931167 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.7142. Min Act: -0.1700
Data Index: 5513445 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.6986. Min Act: -0.1700
Data Index: 8664497 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.6829. Min Act: -0.1700
Data Index: 2555384 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.6673. Min Act: -0.1700
Data Index: 420402 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.6516. Min Act: -0.1700
Data Index: 4602727 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.6673. Min Act: -0.1700
Data Index: 3334814 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.6673. Min Act: -0.1700
Data Index: 593594 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.6516. Min Act: -0.1700
Data Index: 7882295 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8862. Min Range: -3.8862
Max Act: 3.6516. Min Act: -0.1700
Data Index: 6506247 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19