Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3426 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0335. Min Range: -3.0335
Max Act: 3.0335. Min Act: -0.1700
Data Index: 8073558 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0335. Min Range: -3.0335
Max Act: 3.0335. Min Act: -0.1700
Data Index: 5790728 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.9703. Min Act: -0.1700
Data Index: 3878126 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.9545. Min Act: -0.1700
Data Index: 2263414 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.9228. Min Act: -0.1700
Data Index: 3946622 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.9386. Min Act: -0.1700
Data Index: 4475411 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.8911. Min Act: -0.1700
Data Index: 3233034 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.8752. Min Act: -0.1700
Data Index: 2692761 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.8593. Min Act: -0.1700
Data Index: 7307118 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.8593. Min Act: -0.1700
Data Index: 105849 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.8593. Min Act: -0.1700
Data Index: 105850 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.8593. Min Act: -0.1700
Data Index: 6437286 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.8434. Min Act: -0.1700
Data Index: 3233035 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.8434. Min Act: -0.1700
Data Index: 4365548 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.8434. Min Act: -0.1700
Data Index: 1068267 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.8434. Min Act: -0.1700
Data Index: 1322406 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.8116. Min Act: -0.1700
Data Index: 5782495 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.8116. Min Act: -0.1700
Data Index: 5082198 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.8116. Min Act: -0.1700
Data Index: 6860531 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0335. Min Range: -3.0335
Max Act: 2.7957. Min Act: -0.1700
Data Index: 3501823 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19