Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 234 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.7590. Min Act: -0.1700
Data Index: 4024128 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.5715. Min Act: -0.1700
Data Index: 2773732 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.5402. Min Act: -0.1700
Data Index: 2098585 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.5090. Min Act: -0.1700
Data Index: 8491267 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.4777. Min Act: -0.1700
Data Index: 3265432 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.4777. Min Act: -0.1700
Data Index: 4010872 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.4465. Min Act: -0.1700
Data Index: 2692243 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.4152. Min Act: -0.1700
Data Index: 4024129 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.4152. Min Act: -0.1700
Data Index: 7348663 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.3840. Min Act: -0.1700
Data Index: 6275999 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.3840. Min Act: -0.1700
Data Index: 6115556 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.3527. Min Act: -0.1700
Data Index: 1972789 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.3527. Min Act: -0.1700
Data Index: 3130137 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.3527. Min Act: -0.1700
Data Index: 276441 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.3527. Min Act: -0.1700
Data Index: 3107687 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.3215. Min Act: -0.1700
Data Index: 8708210 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.3215. Min Act: -0.1700
Data Index: 8598335 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.3215. Min Act: -0.1700
Data Index: 1573169 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.2902. Min Act: -0.1700
Data Index: 7796796 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7590. Min Range: -4.7590
Max Act: 4.2902. Min Act: -0.1700
Data Index: 6363986 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19