Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2687 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.9355. Min Act: -0.1700
Data Index: 6623665 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.8417. Min Act: -0.1700
Data Index: 4213176 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.7480. Min Act: -0.1700
Data Index: 836791 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.7167. Min Act: -0.1700
Data Index: 7835953 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.7167. Min Act: -0.1700
Data Index: 8492210 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.6855. Min Act: -0.1700
Data Index: 8387956 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.6230. Min Act: -0.1700
Data Index: 2406340 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.5917. Min Act: -0.1700
Data Index: 1030919 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.5917. Min Act: -0.1700
Data Index: 5394860 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.5917. Min Act: -0.1700
Data Index: 7756441 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.5605. Min Act: -0.1700
Data Index: 7092665 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.5292. Min Act: -0.1700
Data Index: 180325 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.5292. Min Act: -0.1700
Data Index: 5567871 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.4980. Min Act: -0.1700
Data Index: 6389 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.4980. Min Act: -0.1700
Data Index: 4929928 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.4980. Min Act: -0.1700
Data Index: 2068074 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.4667. Min Act: -0.1700
Data Index: 7427721 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.4667. Min Act: -0.1700
Data Index: 4155216 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.4042. Min Act: -0.1700
Data Index: 1650247 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9355. Min Range: -6.9355
Max Act: 6.4355. Min Act: -0.1700
Data Index: 1885656 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19