Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3903 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7348. Min Range: -7.7348
Max Act: 7.7348. Min Act: -0.1700
Data Index: 2119753 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7348. Min Range: -7.7348
Max Act: 7.5473. Min Act: -0.1700
Data Index: 1858548 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7348. Min Range: -7.7348
Max Act: 7.4848. Min Act: -0.1700
Data Index: 2995263 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7348. Min Range: -7.7348
Max Act: 7.3598. Min Act: -0.1700
Data Index: 833065 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7348. Min Range: -7.7348
Max Act: 7.2660. Min Act: -0.1700
Data Index: 7867919 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7348. Min Range: -7.7348
Max Act: 7.2348. Min Act: -0.1700
Data Index: 6359444 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7348. Min Range: -7.7348
Max Act: 7.1723. Min Act: -0.1700
Data Index: 2292618 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7348. Min Range: -7.7348
Max Act: 7.1723. Min Act: -0.1700
Data Index: 2922338 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7348. Min Range: -7.7348
Max Act: 7.1410. Min Act: -0.1700
Data Index: 8466289 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7348. Min Range: -7.7348
Max Act: 7.1410. Min Act: -0.1700
Data Index: 800475 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7348. Min Range: -7.7348
Max Act: 7.1410. Min Act: -0.1700
Data Index: 5795615 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7348. Min Range: -7.7348
Max Act: 7.0473. Min Act: -0.1700
Data Index: 8747470 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7348. Min Range: -7.7348
Max Act: 7.0473. Min Act: -0.1700
Data Index: 4867414 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7348. Min Range: -7.7348
Max Act: 7.0160. Min Act: -0.1700
Data Index: 5033055 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7348. Min Range: -7.7348
Max Act: 6.9848. Min Act: -0.1700
Data Index: 4616712 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7348. Min Range: -7.7348
Max Act: 6.8910. Min Act: -0.1700
Data Index: 6565943 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7348. Min Range: -7.7348
Max Act: 6.8910. Min Act: -0.1700
Data Index: 4735886 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7348. Min Range: -7.7348
Max Act: 6.8910. Min Act: -0.1700
Data Index: 8441772 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7348. Min Range: -7.7348
Max Act: 6.8910. Min Act: -0.1700
Data Index: 364185 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7348. Min Range: -7.7348
Max Act: 6.8598. Min Act: -0.1700
Data Index: 3547305 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19