Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4731 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.9887. Min Act: -0.1700
Data Index: 6659822 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.9887. Min Act: -0.1700
Data Index: 6350304 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.8012. Min Act: -0.1700
Data Index: 5762971 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.6137. Min Act: -0.1700
Data Index: 2194847 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.6137. Min Act: -0.1700
Data Index: 146654 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.5512. Min Act: -0.1700
Data Index: 3952769 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.5512. Min Act: -0.1700
Data Index: 5620404 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.4887. Min Act: -0.1700
Data Index: 7684952 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.4575. Min Act: -0.1700
Data Index: 5676214 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.4262. Min Act: -0.1700
Data Index: 6265340 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.4262. Min Act: -0.1700
Data Index: 291628 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.4262. Min Act: -0.1700
Data Index: 468408 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.3950. Min Act: -0.1700
Data Index: 6702340 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.4262. Min Act: -0.1700
Data Index: 1301532 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.3950. Min Act: -0.1700
Data Index: 3577070 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.3325. Min Act: -0.1700
Data Index: 1700879 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.3325. Min Act: -0.1700
Data Index: 8336061 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.3325. Min Act: -0.1700
Data Index: 3381537 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.3325. Min Act: -0.1700
Data Index: 4626947 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9887. Min Range: -7.9887
Max Act: 7.3325. Min Act: -0.1700
Data Index: 2705092 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19