Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3333 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.8188. Min Act: -0.1700
Data Index: 2499947 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.6625. Min Act: -0.1700
Data Index: 5277981 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.5688. Min Act: -0.1700
Data Index: 7402413 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.4750. Min Act: -0.1700
Data Index: 1670853 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.4438. Min Act: -0.1700
Data Index: 6387329 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.4438. Min Act: -0.1700
Data Index: 7496479 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.4125. Min Act: -0.1700
Data Index: 7352705 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.4438. Min Act: -0.1700
Data Index: 1370025 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.3500. Min Act: -0.1700
Data Index: 3577598 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.3188. Min Act: -0.1700
Data Index: 5558678 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.2875. Min Act: -0.1700
Data Index: 4792183 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.2875. Min Act: -0.1700
Data Index: 6950672 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.2875. Min Act: -0.1700
Data Index: 6918452 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.2875. Min Act: -0.1700
Data Index: 461063 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.2563. Min Act: -0.1700
Data Index: 5384107 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.2250. Min Act: -0.1700
Data Index: 8271342 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.2250. Min Act: -0.1700
Data Index: 3194785 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.1625. Min Act: -0.1700
Data Index: 5491734 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.1938. Min Act: -0.1700
Data Index: 319750 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8188. Min Range: -6.8188
Max Act: 6.1938. Min Act: -0.1700
Data Index: 6775944 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19