Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1454 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.9336. Min Act: -0.1700
Data Index: 8614303 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.8086. Min Act: -0.1700
Data Index: 5186993 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.8086. Min Act: -0.1700
Data Index: 3978186 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.7773. Min Act: -0.1700
Data Index: 1721716 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.7148. Min Act: -0.1700
Data Index: 8589980 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.7148. Min Act: -0.1700
Data Index: 7917826 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.6836. Min Act: -0.1700
Data Index: 349333 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.6523. Min Act: -0.1700
Data Index: 7546775 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.6523. Min Act: -0.1700
Data Index: 1501116 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.6523. Min Act: -0.1700
Data Index: 4452368 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.6523. Min Act: -0.1700
Data Index: 4702430 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.6211. Min Act: -0.1700
Data Index: 5559226 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.5898. Min Act: -0.1700
Data Index: 2638226 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.5898. Min Act: -0.1700
Data Index: 1983446 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.5898. Min Act: -0.1700
Data Index: 4903978 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.5586. Min Act: -0.1700
Data Index: 3991489 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.4961. Min Act: -0.1700
Data Index: 7220682 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.5586. Min Act: -0.1700
Data Index: 1284300 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.5273. Min Act: -0.1700
Data Index: 1437649 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9336. Min Range: -4.9336
Max Act: 4.4961. Min Act: -0.1700
Data Index: 7346015 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19