Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4961. Min Range: -6.4961
Max Act: 6.4961. Min Act: -0.1700
Data Index: 5224718 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.9961. Min Act: -0.1700
Data Index: 7838725 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.9961. Min Act: -0.1700
Data Index: 3702328 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.9336. Min Act: -0.1700
Data Index: 8547062 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.9336. Min Act: -0.1700
Data Index: 1442873 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.9336. Min Act: -0.1700
Data Index: 2858459 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.9023. Min Act: -0.1700
Data Index: 7022175 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.8711. Min Act: -0.1700
Data Index: 4064745 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.8398. Min Act: -0.1700
Data Index: 4504321 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.8398. Min Act: -0.1700
Data Index: 3307555 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.8398. Min Act: -0.1700
Data Index: 1160890 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.8398. Min Act: -0.1700
Data Index: 5066743 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.8398. Min Act: -0.1700
Data Index: 8444351 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.8086. Min Act: -0.1700
Data Index: 7554666 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.7773. Min Act: -0.1700
Data Index: 8191268 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.7773. Min Act: -0.1700
Data Index: 2105054 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.7773. Min Act: -0.1700
Data Index: 242404 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.7773. Min Act: -0.1700
Data Index: 5965198 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.7461. Min Act: -0.1700
Data Index: 2257934 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4961. Min Range: -6.4961
Max Act: 5.7461. Min Act: -0.1700
Data Index: 1798839 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19