Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3794 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.8697. Min Act: -0.1700
Data Index: 3275240 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.8385. Min Act: -0.1700
Data Index: 8567866 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.7760. Min Act: -0.1700
Data Index: 5526123 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.6822. Min Act: -0.1700
Data Index: 4567069 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.7135. Min Act: -0.1700
Data Index: 5202439 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.6510. Min Act: -0.1700
Data Index: 7812099 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.6510. Min Act: -0.1700
Data Index: 7345430 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.5885. Min Act: -0.1700
Data Index: 7003243 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.5885. Min Act: -0.1700
Data Index: 454660 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.5885. Min Act: -0.1700
Data Index: 8080334 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.5885. Min Act: -0.1700
Data Index: 4567068 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.5260. Min Act: -0.1700
Data Index: 954076 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.5572. Min Act: -0.1700
Data Index: 1461760 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.5572. Min Act: -0.1700
Data Index: 6161740 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.5572. Min Act: -0.1700
Data Index: 4077977 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.5572. Min Act: -0.1700
Data Index: 4236344 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.5572. Min Act: -0.1700
Data Index: 1836213 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.5572. Min Act: -0.1700
Data Index: 8823025 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.5572. Min Act: -0.1700
Data Index: 3610601 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8697. Min Range: -5.8697
Max Act: 5.4947. Min Act: -0.1700
Data Index: 8280180 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19