Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1994 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2604. Min Range: -7.2604
Max Act: 7.2604. Min Act: -0.1700
Data Index: 795774 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2604. Min Range: -7.2604
Max Act: 7.1667. Min Act: -0.1700
Data Index: 3544852 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2604. Min Range: -7.2604
Max Act: 7.1354. Min Act: -0.1700
Data Index: 2178105 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2604. Min Range: -7.2604
Max Act: 7.0104. Min Act: -0.1700
Data Index: 3844369 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2604. Min Range: -7.2604
Max Act: 7.0104. Min Act: -0.1700
Data Index: 5630550 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2604. Min Range: -7.2604
Max Act: 6.9479. Min Act: -0.1700
Data Index: 4676308 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2604. Min Range: -7.2604
Max Act: 6.9167. Min Act: -0.1700
Data Index: 7881718 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2604. Min Range: -7.2604
Max Act: 6.8854. Min Act: -0.1700
Data Index: 323621 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2604. Min Range: -7.2604
Max Act: 6.8854. Min Act: -0.1700
Data Index: 1899405 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2604. Min Range: -7.2604
Max Act: 6.8542. Min Act: -0.1700
Data Index: 7819630 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2604. Min Range: -7.2604
Max Act: 6.8542. Min Act: -0.1700
Data Index: 699380 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2604. Min Range: -7.2604
Max Act: 6.8229. Min Act: -0.1700
Data Index: 5991969 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2604. Min Range: -7.2604
Max Act: 6.8229. Min Act: -0.1700
Data Index: 104374 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2604. Min Range: -7.2604
Max Act: 6.8229. Min Act: -0.1700
Data Index: 6396826 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2604. Min Range: -7.2604
Max Act: 6.7604. Min Act: -0.1700
Data Index: 4052100 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2604. Min Range: -7.2604
Max Act: 6.7917. Min Act: -0.1700
Data Index: 8519394 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2604. Min Range: -7.2604
Max Act: 6.6667. Min Act: -0.1700
Data Index: 2612467 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2604. Min Range: -7.2604
Max Act: 6.6667. Min Act: -0.1700
Data Index: 7881717 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2604. Min Range: -7.2604
Max Act: 6.6667. Min Act: -0.1700
Data Index: 5991350 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2604. Min Range: -7.2604
Max Act: 6.6354. Min Act: -0.1700
Data Index: 1535153 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19