Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1804 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1738. Min Range: -9.1738
Max Act: 9.1738. Min Act: -0.1700
Data Index: 6531395 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.7988. Min Act: -0.1700
Data Index: 2019675 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.6113. Min Act: -0.1700
Data Index: 1040154 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.5488. Min Act: -0.1700
Data Index: 1753802 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.5488. Min Act: -0.1700
Data Index: 3796230 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.5488. Min Act: -0.1700
Data Index: 8030211 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.4863. Min Act: -0.1700
Data Index: 8289833 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.4863. Min Act: -0.1700
Data Index: 6431628 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.4238. Min Act: -0.1700
Data Index: 5440264 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.4238. Min Act: -0.1700
Data Index: 1949205 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.4238. Min Act: -0.1700
Data Index: 1816477 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.4238. Min Act: -0.1700
Data Index: 2477145 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.4238. Min Act: -0.1700
Data Index: 8821438 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.2988. Min Act: -0.1700
Data Index: 6942689 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.2988. Min Act: -0.1700
Data Index: 8624195 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.2988. Min Act: -0.1700
Data Index: 1242503 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.2988. Min Act: -0.1700
Data Index: 7640455 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.2988. Min Act: -0.1700
Data Index: 7394751 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.2988. Min Act: -0.1700
Data Index: 4418083 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1738. Min Range: -9.1738
Max Act: 8.3613. Min Act: -0.1700
Data Index: 41386 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19