Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2672 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4480. Min Range: -7.4480
Max Act: 7.4480. Min Act: -0.1700
Data Index: 71332 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.9792. Min Act: -0.1700
Data Index: 7928765 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.9167. Min Act: -0.1700
Data Index: 6096728 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.8230. Min Act: -0.1700
Data Index: 2376271 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.8230. Min Act: -0.1700
Data Index: 6112847 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.7917. Min Act: -0.1700
Data Index: 4016915 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.7917. Min Act: -0.1700
Data Index: 4272798 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.7292. Min Act: -0.1700
Data Index: 697287 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.6980. Min Act: -0.1700
Data Index: 6949324 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.7292. Min Act: -0.1700
Data Index: 7494373 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.6667. Min Act: -0.1700
Data Index: 6759481 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.6980. Min Act: -0.1700
Data Index: 1642085 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.6667. Min Act: -0.1700
Data Index: 1408983 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.6355. Min Act: -0.1700
Data Index: 2620690 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.6355. Min Act: -0.1700
Data Index: 7993992 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.5730. Min Act: -0.1700
Data Index: 26206 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.5730. Min Act: -0.1700
Data Index: 884526 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.5105. Min Act: -0.1700
Data Index: 4690865 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.5417. Min Act: -0.1700
Data Index: 4003243 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4480. Min Range: -7.4480
Max Act: 6.5417. Min Act: -0.1700
Data Index: 2885233 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19