Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3247 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4084. Min Range: -7.4084
Max Act: 7.4084. Min Act: -0.1700
Data Index: 3557292 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4084. Min Range: -7.4084
Max Act: 7.3459. Min Act: -0.1700
Data Index: 2043262 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4084. Min Range: -7.4084
Max Act: 7.0959. Min Act: -0.1700
Data Index: 5335426 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4084. Min Range: -7.4084
Max Act: 6.9709. Min Act: -0.1700
Data Index: 8438225 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4084. Min Range: -7.4084
Max Act: 6.8459. Min Act: -0.1700
Data Index: 3677792 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4084. Min Range: -7.4084
Max Act: 6.8459. Min Act: -0.1700
Data Index: 1513032 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4084. Min Range: -7.4084
Max Act: 6.7834. Min Act: -0.1700
Data Index: 2113425 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4084. Min Range: -7.4084
Max Act: 6.7834. Min Act: -0.1700
Data Index: 4238913 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4084. Min Range: -7.4084
Max Act: 6.7522. Min Act: -0.1700
Data Index: 1730647 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4084. Min Range: -7.4084
Max Act: 6.7522. Min Act: -0.1700
Data Index: 6913831 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4084. Min Range: -7.4084
Max Act: 6.7522. Min Act: -0.1700
Data Index: 2828141 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4084. Min Range: -7.4084
Max Act: 6.7522. Min Act: -0.1700
Data Index: 5928524 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4084. Min Range: -7.4084
Max Act: 6.7209. Min Act: -0.1700
Data Index: 3705618 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4084. Min Range: -7.4084
Max Act: 6.7522. Min Act: -0.1700
Data Index: 4324785 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4084. Min Range: -7.4084
Max Act: 6.7209. Min Act: -0.1700
Data Index: 5488250 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4084. Min Range: -7.4084
Max Act: 6.7209. Min Act: -0.1700
Data Index: 6630971 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4084. Min Range: -7.4084
Max Act: 6.7209. Min Act: -0.1700
Data Index: 5195865 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4084. Min Range: -7.4084
Max Act: 6.6897. Min Act: -0.1700
Data Index: 993900 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4084. Min Range: -7.4084
Max Act: 6.6897. Min Act: -0.1700
Data Index: 6092796 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4084. Min Range: -7.4084
Max Act: 6.6897. Min Act: -0.1700
Data Index: 8062971 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19