Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 370 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.6235. Min Act: -0.1700
Data Index: 4433352 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.6235. Min Act: -0.1700
Data Index: 2761936 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5711. Min Act: -0.1700
Data Index: 106547 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5711. Min Act: -0.1700
Data Index: 7672234 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5536. Min Act: -0.1700
Data Index: 2139687 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5536. Min Act: -0.1700
Data Index: 2152349 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5361. Min Act: -0.1700
Data Index: 7321521 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5536. Min Act: -0.1700
Data Index: 1770496 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5361. Min Act: -0.1700
Data Index: 6435040 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5361. Min Act: -0.1700
Data Index: 7612105 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5186. Min Act: -0.1700
Data Index: 1907258 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5536. Min Act: -0.1700
Data Index: 7173986 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5361. Min Act: -0.1698
Data Index: 6561280 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5361. Min Act: -0.1700
Data Index: 5004011 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5186. Min Act: -0.1700
Data Index: 6923516 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5186. Min Act: -0.1699
Data Index: 3646073 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5186. Min Act: -0.1699
Data Index: 7965617 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5186. Min Act: -0.1700
Data Index: 4433351 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5010. Min Act: -0.1700
Data Index: 4547471 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6235. Min Range: -1.6235
Max Act: 1.5186. Min Act: -0.1700
Data Index: 562513 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19