Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3185 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4410. Min Range: -8.4410
Max Act: 8.4410. Min Act: -0.1700
Data Index: 8188049 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4410. Min Range: -8.4410
Max Act: 8.1285. Min Act: -0.1700
Data Index: 8699601 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.8785. Min Act: -0.1700
Data Index: 6450603 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.8785. Min Act: -0.1700
Data Index: 2688528 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.8160. Min Act: -0.1700
Data Index: 7879276 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.8160. Min Act: -0.1700
Data Index: 2181444 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.7535. Min Act: -0.1700
Data Index: 4046689 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.6910. Min Act: -0.1700
Data Index: 7121266 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.6910. Min Act: -0.1700
Data Index: 5094965 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.6910. Min Act: -0.1700
Data Index: 147695 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.6910. Min Act: -0.1700
Data Index: 6941527 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.6285. Min Act: -0.1700
Data Index: 3132598 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.5660. Min Act: -0.1700
Data Index: 6159535 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.5660. Min Act: -0.1700
Data Index: 3880585 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.5660. Min Act: -0.1700
Data Index: 1255937 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.5660. Min Act: -0.1700
Data Index: 5767597 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.5035. Min Act: -0.1700
Data Index: 4573726 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.6285. Min Act: -0.1700
Data Index: 7616662 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.5660. Min Act: -0.1700
Data Index: 6411501 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4410. Min Range: -8.4410
Max Act: 7.5660. Min Act: -0.1700
Data Index: 6818399 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19