Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 503 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.8481. Min Act: -0.1700
Data Index: 1840616 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.7231. Min Act: -0.1700
Data Index: 7455154 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.7231. Min Act: -0.1700
Data Index: 5990916 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.6606. Min Act: -0.1700
Data Index: 4600291 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.5981. Min Act: -0.1700
Data Index: 4962953 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.5356. Min Act: -0.1700
Data Index: 8524484 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.5356. Min Act: -0.1700
Data Index: 8099752 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.5356. Min Act: -0.1700
Data Index: 658853 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.4731. Min Act: -0.1700
Data Index: 3412494 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.4106. Min Act: -0.1700
Data Index: 4112973 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.3481. Min Act: -0.1700
Data Index: 1760128 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.3481. Min Act: -0.1700
Data Index: 8141877 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.2856. Min Act: -0.1700
Data Index: 6600024 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.2856. Min Act: -0.1700
Data Index: 3573190 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.2856. Min Act: -0.1700
Data Index: 8778476 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.2856. Min Act: -0.1700
Data Index: 217550 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.2231. Min Act: -0.1700
Data Index: 1760124 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.2231. Min Act: -0.1700
Data Index: 1804040 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.1606. Min Act: -0.1700
Data Index: 1703934 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8481. Min Range: -9.8481
Max Act: 9.1606. Min Act: -0.1700
Data Index: 8222322 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19