Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2780 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.8647. Min Act: -0.1700
Data Index: 8531399 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.8647. Min Act: -0.1700
Data Index: 3475172 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.7709. Min Act: -0.1700
Data Index: 3076511 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.7397. Min Act: -0.1700
Data Index: 821160 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.7084. Min Act: -0.1700
Data Index: 1290716 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.7397. Min Act: -0.1700
Data Index: 3191363 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.7397. Min Act: -0.1700
Data Index: 2481703 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.7397. Min Act: -0.1700
Data Index: 911725 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.6772. Min Act: -0.1700
Data Index: 8223822 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.7084. Min Act: -0.1700
Data Index: 949991 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.7084. Min Act: -0.1700
Data Index: 8404918 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.7084. Min Act: -0.1700
Data Index: 4285593 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.6772. Min Act: -0.1700
Data Index: 911724 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.6772. Min Act: -0.1700
Data Index: 2851010 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.6772. Min Act: -0.1700
Data Index: 5668881 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.6459. Min Act: -0.1700
Data Index: 4256265 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.6772. Min Act: -0.1700
Data Index: 7544108 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.6772. Min Act: -0.1700
Data Index: 6635153 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.6772. Min Act: -0.1700
Data Index: 6247635 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8647. Min Range: -4.8647
Max Act: 4.6772. Min Act: -0.1700
Data Index: 3276818 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19