Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1688 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4182. Min Range: -6.4182
Max Act: 6.4182. Min Act: -0.1700
Data Index: 5680958 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4182. Min Range: -6.4182
Max Act: 6.1370. Min Act: -0.1700
Data Index: 5658143 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4182. Min Range: -6.4182
Max Act: 6.0745. Min Act: -0.1700
Data Index: 6614431 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4182. Min Range: -6.4182
Max Act: 5.9807. Min Act: -0.1700
Data Index: 353091 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4182. Min Range: -6.4182
Max Act: 5.9495. Min Act: -0.1700
Data Index: 5319753 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4182. Min Range: -6.4182
Max Act: 5.9182. Min Act: -0.1700
Data Index: 1510998 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4182. Min Range: -6.4182
Max Act: 5.8870. Min Act: -0.1700
Data Index: 6987377 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4182. Min Range: -6.4182
Max Act: 5.8870. Min Act: -0.1700
Data Index: 3241664 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4182. Min Range: -6.4182
Max Act: 5.8245. Min Act: -0.1700
Data Index: 8149392 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4182. Min Range: -6.4182
Max Act: 5.8245. Min Act: -0.1700
Data Index: 2556420 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4182. Min Range: -6.4182
Max Act: 5.8245. Min Act: -0.1700
Data Index: 5207660 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4182. Min Range: -6.4182
Max Act: 5.8245. Min Act: -0.1700
Data Index: 2556997 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4182. Min Range: -6.4182
Max Act: 5.7932. Min Act: -0.1700
Data Index: 5819949 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4182. Min Range: -6.4182
Max Act: 5.8245. Min Act: -0.1700
Data Index: 8630794 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4182. Min Range: -6.4182
Max Act: 5.7620. Min Act: -0.1700
Data Index: 3491472 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4182. Min Range: -6.4182
Max Act: 5.7620. Min Act: -0.1700
Data Index: 3859554 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4182. Min Range: -6.4182
Max Act: 5.7932. Min Act: -0.1700
Data Index: 2506236 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4182. Min Range: -6.4182
Max Act: 5.7932. Min Act: -0.1700
Data Index: 8271952 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4182. Min Range: -6.4182
Max Act: 5.7932. Min Act: -0.1700
Data Index: 6295885 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4182. Min Range: -6.4182
Max Act: 5.7307. Min Act: -0.1700
Data Index: 4110420 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19