Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3105 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.8697. Min Act: -0.1700
Data Index: 612128 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.8385. Min Act: -0.1700
Data Index: 3298784 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.8072. Min Act: -0.1700
Data Index: 8259491 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.7135. Min Act: -0.1700
Data Index: 217916 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.7135. Min Act: -0.1700
Data Index: 1610971 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.6822. Min Act: -0.1700
Data Index: 5531903 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.6822. Min Act: -0.1700
Data Index: 6331799 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.6510. Min Act: -0.1700
Data Index: 8144789 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.6510. Min Act: -0.1700
Data Index: 3938933 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.6510. Min Act: -0.1700
Data Index: 2967080 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.6197. Min Act: -0.1700
Data Index: 7562681 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.6197. Min Act: -0.1700
Data Index: 4251304 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.5885. Min Act: -0.1700
Data Index: 5690544 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.5572. Min Act: -0.1700
Data Index: 4378563 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.4947. Min Act: -0.1700
Data Index: 5367490 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.4635. Min Act: -0.1700
Data Index: 1750013 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.4635. Min Act: -0.1700
Data Index: 3938935 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.4635. Min Act: -0.1700
Data Index: 440923 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.4010. Min Act: -0.1700
Data Index: 2336851 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8697. Min Range: -4.8697
Max Act: 4.4322. Min Act: -0.1700
Data Index: 5400875 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19