Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.7410. Min Act: -0.1700
Data Index: 1793432 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.7410. Min Act: -0.1700
Data Index: 2111538 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.7098. Min Act: -0.1700
Data Index: 2739368 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.6473. Min Act: -0.1700
Data Index: 4496320 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.5848. Min Act: -0.1700
Data Index: 7199309 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.5848. Min Act: -0.1700
Data Index: 5058930 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.5535. Min Act: -0.1700
Data Index: 6590636 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.5223. Min Act: -0.1700
Data Index: 8588030 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.4910. Min Act: -0.1700
Data Index: 3040311 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.4910. Min Act: -0.1700
Data Index: 8529707 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.4598. Min Act: -0.1700
Data Index: 7098151 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.4598. Min Act: -0.1700
Data Index: 4532499 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.4598. Min Act: -0.1700
Data Index: 4195403 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.4285. Min Act: -0.1700
Data Index: 8827315 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.3973. Min Act: -0.1700
Data Index: 4736820 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.3973. Min Act: -0.1700
Data Index: 8160336 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.3348. Min Act: -0.1700
Data Index: 8524700 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.3348. Min Act: -0.1700
Data Index: 124926 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.3348. Min Act: -0.1700
Data Index: 7109769 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7410. Min Range: -6.7410
Max Act: 6.3348. Min Act: -0.1700
Data Index: 848630 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19