Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 10 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7793. Min Range: -6.7793
Max Act: 6.7793. Min Act: -0.1700
Data Index: 6165587 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7793. Min Range: -6.7793
Max Act: 6.7480. Min Act: -0.1700
Data Index: 677502 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7793. Min Range: -6.7793
Max Act: 6.4980. Min Act: -0.1700
Data Index: 4008096 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7793. Min Range: -6.7793
Max Act: 6.3105. Min Act: -0.1700
Data Index: 1752533 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7793. Min Range: -6.7793
Max Act: 6.1230. Min Act: -0.1700
Data Index: 5528079 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7793. Min Range: -6.7793
Max Act: 6.1230. Min Act: -0.1700
Data Index: 2445478 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7793. Min Range: -6.7793
Max Act: 5.9980. Min Act: -0.1700
Data Index: 6173271 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7793. Min Range: -6.7793
Max Act: 5.9355. Min Act: -0.1700
Data Index: 1622025 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7793. Min Range: -6.7793
Max Act: 5.9355. Min Act: -0.1700
Data Index: 4044361 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7793. Min Range: -6.7793
Max Act: 5.9355. Min Act: -0.1700
Data Index: 4448333 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7793. Min Range: -6.7793
Max Act: 5.9668. Min Act: -0.1700
Data Index: 1809267 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7793. Min Range: -6.7793
Max Act: 5.9355. Min Act: -0.1700
Data Index: 3078869 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7793. Min Range: -6.7793
Max Act: 5.8730. Min Act: -0.1700
Data Index: 2413720 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7793. Min Range: -6.7793
Max Act: 5.9043. Min Act: -0.1700
Data Index: 4289478 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7793. Min Range: -6.7793
Max Act: 5.9043. Min Act: -0.1700
Data Index: 8063287 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7793. Min Range: -6.7793
Max Act: 5.9043. Min Act: -0.1700
Data Index: 5461029 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7793. Min Range: -6.7793
Max Act: 5.8418. Min Act: -0.1700
Data Index: 5237532 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7793. Min Range: -6.7793
Max Act: 5.8105. Min Act: -0.1700
Data Index: 199811 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7793. Min Range: -6.7793
Max Act: 5.8105. Min Act: -0.1700
Data Index: 1622029 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7793. Min Range: -6.7793
Max Act: 5.8105. Min Act: -0.1700
Data Index: 5126017 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19