Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 52 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.7702. Min Act: -0.1700
Data Index: 3600884 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.7077. Min Act: -0.1700
Data Index: 1705122 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.7077. Min Act: -0.1700
Data Index: 3135173 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.6765. Min Act: -0.1700
Data Index: 1838369 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.6452. Min Act: -0.1700
Data Index: 3135170 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.6140. Min Act: -0.1700
Data Index: 1838360 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.5827. Min Act: -0.1700
Data Index: 8617766 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.6140. Min Act: -0.1700
Data Index: 3838075 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.5827. Min Act: -0.1700
Data Index: 4581527 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.5515. Min Act: -0.1700
Data Index: 296775 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.5202. Min Act: -0.1700
Data Index: 8267872 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.5202. Min Act: -0.1700
Data Index: 192959 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.4890. Min Act: -0.1700
Data Index: 5377230 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.5202. Min Act: -0.1700
Data Index: 1838364 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.4890. Min Act: -0.1700
Data Index: 5851255 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.4890. Min Act: -0.1700
Data Index: 1135978 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.4890. Min Act: -0.1700
Data Index: 5401704 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.4577. Min Act: -0.1700
Data Index: 3616980 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.4577. Min Act: -0.1700
Data Index: 7146384 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7702. Min Range: -4.7702
Max Act: 4.4577. Min Act: -0.1700
Data Index: 5213192 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19