Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3436 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0918. Min Range: -6.0918
Max Act: 6.0918. Min Act: -0.1700
Data Index: 2816694 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.9668. Min Act: -0.1700
Data Index: 1092128 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.9668. Min Act: -0.1700
Data Index: 4803564 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.9668. Min Act: -0.1700
Data Index: 5880575 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.9355. Min Act: -0.1700
Data Index: 1952369 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.9668. Min Act: -0.1700
Data Index: 668395 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.8418. Min Act: -0.1700
Data Index: 3325886 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.8730. Min Act: -0.1700
Data Index: 3244310 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.8418. Min Act: -0.1700
Data Index: 3189602 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.7793. Min Act: -0.1700
Data Index: 1010217 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.7793. Min Act: -0.1700
Data Index: 7394141 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.7793. Min Act: -0.1700
Data Index: 4173718 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.7480. Min Act: -0.1700
Data Index: 1592735 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.7793. Min Act: -0.1700
Data Index: 7552154 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.7168. Min Act: -0.1700
Data Index: 4415767 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.7480. Min Act: -0.1700
Data Index: 2257298 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.7480. Min Act: -0.1700
Data Index: 4791237 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.7480. Min Act: -0.1700
Data Index: 5965996 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.7168. Min Act: -0.1700
Data Index: 995247 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.6855. Min Act: -0.1700
Data Index: 3694771 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19