Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3962. Min Range: -6.3962
Max Act: 6.3962. Min Act: -0.1700
Data Index: 6031468 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3962. Min Range: -6.3962
Max Act: 6.1462. Min Act: -0.1700
Data Index: 6517908 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3962. Min Range: -6.3962
Max Act: 6.0837. Min Act: -0.1700
Data Index: 8244612 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3962. Min Range: -6.3962
Max Act: 6.0837. Min Act: -0.1700
Data Index: 7337940 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3962. Min Range: -6.3962
Max Act: 6.1150. Min Act: -0.1700
Data Index: 7429926 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3962. Min Range: -6.3962
Max Act: 6.0525. Min Act: -0.1700
Data Index: 1119998 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3962. Min Range: -6.3962
Max Act: 6.0525. Min Act: -0.1700
Data Index: 1818297 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3962. Min Range: -6.3962
Max Act: 6.0212. Min Act: -0.1700
Data Index: 2766637 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3962. Min Range: -6.3962
Max Act: 5.9900. Min Act: -0.1700
Data Index: 3154572 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3962. Min Range: -6.3962
Max Act: 5.9900. Min Act: -0.1700
Data Index: 5826800 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3962. Min Range: -6.3962
Max Act: 5.9587. Min Act: -0.1700
Data Index: 4778584 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3962. Min Range: -6.3962
Max Act: 5.9587. Min Act: -0.1700
Data Index: 3967862 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3962. Min Range: -6.3962
Max Act: 5.9275. Min Act: -0.1700
Data Index: 5178294 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3962. Min Range: -6.3962
Max Act: 5.9275. Min Act: -0.1700
Data Index: 3989434 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3962. Min Range: -6.3962
Max Act: 5.8650. Min Act: -0.1700
Data Index: 7428895 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3962. Min Range: -6.3962
Max Act: 5.8337. Min Act: -0.1700
Data Index: 7399113 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3962. Min Range: -6.3962
Max Act: 5.8650. Min Act: -0.1700
Data Index: 7783844 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3962. Min Range: -6.3962
Max Act: 5.8337. Min Act: -0.1700
Data Index: 5292669 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3962. Min Range: -6.3962
Max Act: 5.8650. Min Act: -0.1700
Data Index: 5011033 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3962. Min Range: -6.3962
Max Act: 5.8337. Min Act: -0.1700
Data Index: 3174419 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19