Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4710 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8098. Min Range: -5.8098
Max Act: 5.8098. Min Act: -0.1700
Data Index: 7126074 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8098. Min Range: -5.8098
Max Act: 5.1848. Min Act: -0.1700
Data Index: 5376251 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8098. Min Range: -5.8098
Max Act: 5.1223. Min Act: -0.1700
Data Index: 7788160 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8098. Min Range: -5.8098
Max Act: 5.0910. Min Act: -0.1700
Data Index: 2427043 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8098. Min Range: -5.8098
Max Act: 5.0598. Min Act: -0.1700
Data Index: 1011010 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8098. Min Range: -5.8098
Max Act: 5.0598. Min Act: -0.1700
Data Index: 1795379 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8098. Min Range: -5.8098
Max Act: 5.0598. Min Act: -0.1700
Data Index: 7858768 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8098. Min Range: -5.8098
Max Act: 5.0285. Min Act: -0.1700
Data Index: 6469190 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8098. Min Range: -5.8098
Max Act: 5.0285. Min Act: -0.1700
Data Index: 4670934 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8098. Min Range: -5.8098
Max Act: 4.9660. Min Act: -0.1700
Data Index: 3783074 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8098. Min Range: -5.8098
Max Act: 4.9660. Min Act: -0.1700
Data Index: 20950 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8098. Min Range: -5.8098
Max Act: 4.9348. Min Act: -0.1700
Data Index: 6427238 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8098. Min Range: -5.8098
Max Act: 4.9035. Min Act: -0.1700
Data Index: 3191616 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8098. Min Range: -5.8098
Max Act: 4.8723. Min Act: -0.1700
Data Index: 3015229 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8098. Min Range: -5.8098
Max Act: 4.8410. Min Act: -0.1700
Data Index: 2268754 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8098. Min Range: -5.8098
Max Act: 4.8410. Min Act: -0.1700
Data Index: 2487605 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8098. Min Range: -5.8098
Max Act: 4.8098. Min Act: -0.1700
Data Index: 1916838 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8098. Min Range: -5.8098
Max Act: 4.8098. Min Act: -0.1700
Data Index: 5877481 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8098. Min Range: -5.8098
Max Act: 4.8410. Min Act: -0.1700
Data Index: 6439934 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8098. Min Range: -5.8098
Max Act: 4.7785. Min Act: -0.1700
Data Index: 1035118 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19