Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3052 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7153. Min Range: -6.7153
Max Act: 6.7153. Min Act: -0.1700
Data Index: 6506902 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7153. Min Range: -6.7153
Max Act: 6.4965. Min Act: -0.1700
Data Index: 3402026 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7153. Min Range: -6.7153
Max Act: 6.2778. Min Act: -0.1700
Data Index: 5740091 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7153. Min Range: -6.7153
Max Act: 6.2465. Min Act: -0.1700
Data Index: 4681901 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7153. Min Range: -6.7153
Max Act: 6.0278. Min Act: -0.1700
Data Index: 1386066 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7153. Min Range: -6.7153
Max Act: 6.0278. Min Act: -0.1700
Data Index: 6458164 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7153. Min Range: -6.7153
Max Act: 6.0278. Min Act: -0.1700
Data Index: 5945392 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7153. Min Range: -6.7153
Max Act: 6.0278. Min Act: -0.1700
Data Index: 1478522 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7153. Min Range: -6.7153
Max Act: 5.9965. Min Act: -0.1700
Data Index: 1988076 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7153. Min Range: -6.7153
Max Act: 6.0278. Min Act: -0.1700
Data Index: 4300016 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7153. Min Range: -6.7153
Max Act: 5.9965. Min Act: -0.1700
Data Index: 2559624 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7153. Min Range: -6.7153
Max Act: 5.9653. Min Act: -0.1700
Data Index: 336451 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7153. Min Range: -6.7153
Max Act: 5.9653. Min Act: -0.1700
Data Index: 4539846 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7153. Min Range: -6.7153
Max Act: 5.9653. Min Act: -0.1700
Data Index: 8468103 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7153. Min Range: -6.7153
Max Act: 5.9653. Min Act: -0.1700
Data Index: 2882313 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7153. Min Range: -6.7153
Max Act: 5.9340. Min Act: -0.1700
Data Index: 4161612 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7153. Min Range: -6.7153
Max Act: 5.9340. Min Act: -0.1700
Data Index: 2477868 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7153. Min Range: -6.7153
Max Act: 5.9653. Min Act: -0.1700
Data Index: 831752 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7153. Min Range: -6.7153
Max Act: 5.9340. Min Act: -0.1700
Data Index: 637783 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7153. Min Range: -6.7153
Max Act: 5.9340. Min Act: -0.1700
Data Index: 3924369 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19