Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3362 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.9165. Min Act: -0.1700
Data Index: 8532123 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.9165. Min Act: -0.1700
Data Index: 4432153 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.7915. Min Act: -0.1700
Data Index: 1012162 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.7602. Min Act: -0.1700
Data Index: 6514621 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.7602. Min Act: -0.1700
Data Index: 2575686 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.7290. Min Act: -0.1700
Data Index: 6769056 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.6977. Min Act: -0.1700
Data Index: 3931584 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.6977. Min Act: -0.1700
Data Index: 3811521 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.6352. Min Act: -0.1700
Data Index: 2697486 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.6040. Min Act: -0.1700
Data Index: 7001267 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.6040. Min Act: -0.1700
Data Index: 5650332 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.5415. Min Act: -0.1700
Data Index: 8400980 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.5727. Min Act: -0.1700
Data Index: 4186318 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.5415. Min Act: -0.1700
Data Index: 875051 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.5102. Min Act: -0.1700
Data Index: 8354071 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.5102. Min Act: -0.1700
Data Index: 6028806 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.5102. Min Act: -0.1700
Data Index: 1876515 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.5102. Min Act: -0.1700
Data Index: 1120343 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.4790. Min Act: -0.1700
Data Index: 7323231 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9165. Min Range: -5.9165
Max Act: 5.5102. Min Act: -0.1700
Data Index: 2883319 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19