Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4955 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0584. Min Range: -3.0584
Max Act: 3.0584. Min Act: -0.1700
Data Index: 3667460 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.9794. Min Act: -0.1700
Data Index: 2510544 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.8685. Min Act: -0.1700
Data Index: 8366210 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.8367. Min Act: -0.1700
Data Index: 2119159 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.8208. Min Act: -0.1700
Data Index: 1946351 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.8208. Min Act: -0.1700
Data Index: 2310114 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.8208. Min Act: -0.1700
Data Index: 3928118 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.8208. Min Act: -0.1700
Data Index: 3361865 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.8049. Min Act: -0.1700
Data Index: 5787504 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.8049. Min Act: -0.1700
Data Index: 1958253 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.7731. Min Act: -0.1700
Data Index: 8213077 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.7890. Min Act: -0.1700
Data Index: 7868642 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.7890. Min Act: -0.1700
Data Index: 111866 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.7731. Min Act: -0.1700
Data Index: 64363 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.7731. Min Act: -0.1700
Data Index: 5154093 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.7731. Min Act: -0.1700
Data Index: 1813622 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.7731. Min Act: -0.1700
Data Index: 5209311 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.7731. Min Act: -0.1700
Data Index: 7451702 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.7731. Min Act: -0.1700
Data Index: 7278836 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0584. Min Range: -3.0584
Max Act: 2.7571. Min Act: -0.1700
Data Index: 5569074 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19