Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1464 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.8410. Min Act: -0.1700
Data Index: 329288 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.7785. Min Act: -0.1700
Data Index: 2631095 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.7785. Min Act: -0.1700
Data Index: 3196017 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.7473. Min Act: -0.1700
Data Index: 568226 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.7473. Min Act: -0.1700
Data Index: 376449 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.7785. Min Act: -0.1700
Data Index: 2185501 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.6848. Min Act: -0.1700
Data Index: 5015212 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.6535. Min Act: -0.1700
Data Index: 8551297 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.6535. Min Act: -0.1700
Data Index: 4510716 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.6535. Min Act: -0.1700
Data Index: 3125445 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.5910. Min Act: -0.1700
Data Index: 2880055 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.5598. Min Act: -0.1700
Data Index: 4942405 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.4973. Min Act: -0.1700
Data Index: 2584790 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.5285. Min Act: -0.1700
Data Index: 882323 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.4660. Min Act: -0.1700
Data Index: 5047003 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.4348. Min Act: -0.1700
Data Index: 3610335 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.4660. Min Act: -0.1700
Data Index: 3904866 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.3723. Min Act: -0.1700
Data Index: 7116385 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.4035. Min Act: -0.1700
Data Index: 2919924 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8410. Min Range: -6.8410
Max Act: 6.3410. Min Act: -0.1700
Data Index: 6428720 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19