Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 0 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0098. Min Range: -2.0098
Max Act: 2.0098. Min Act: -0.1700
Data Index: 4900778 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.9505. Min Act: -0.1700
Data Index: 2790337 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.9420. Min Act: -0.1700
Data Index: 7739594 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.9080. Min Act: -0.1700
Data Index: 1878256 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.9165. Min Act: -0.1700
Data Index: 4630076 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.8909. Min Act: -0.1700
Data Index: 318155 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.8995. Min Act: -0.1700
Data Index: 4652677 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.8909. Min Act: -0.1700
Data Index: 7437583 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.8909. Min Act: -0.1700
Data Index: 3625020 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.8995. Min Act: -0.1700
Data Index: 1020165 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.8909. Min Act: -0.1700
Data Index: 5321165 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.8824. Min Act: -0.1700
Data Index: 6176000 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.8824. Min Act: -0.1700
Data Index: 266990 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.8739. Min Act: -0.1700
Data Index: 1007262 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.8824. Min Act: -0.1700
Data Index: 4340873 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.8568. Min Act: -0.1699
Data Index: 561958 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.8739. Min Act: -0.1700
Data Index: 4399439 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.8653. Min Act: -0.1700
Data Index: 6088121 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.8653. Min Act: -0.1700
Data Index: 3044973 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0098. Min Range: -2.0098
Max Act: 1.8653. Min Act: -0.1700
Data Index: 3699041 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19