Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3679 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1310. Min Range: -4.1310
Max Act: 4.1310. Min Act: -0.1700
Data Index: 2224269 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1310. Min Range: -4.1310
Max Act: 4.0372. Min Act: -0.1700
Data Index: 2426258 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1310. Min Range: -4.1310
Max Act: 4.0060. Min Act: -0.1700
Data Index: 385860 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1310. Min Range: -4.1310
Max Act: 3.9747. Min Act: -0.1700
Data Index: 2915959 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1310. Min Range: -4.1310
Max Act: 3.9434. Min Act: -0.1700
Data Index: 8631383 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1310. Min Range: -4.1310
Max Act: 3.9434. Min Act: -0.1700
Data Index: 3742617 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1310. Min Range: -4.1310
Max Act: 3.9434. Min Act: -0.1700
Data Index: 6459588 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1310. Min Range: -4.1310
Max Act: 3.9122. Min Act: -0.1700
Data Index: 962680 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1310. Min Range: -4.1310
Max Act: 3.9122. Min Act: -0.1700
Data Index: 5942610 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1310. Min Range: -4.1310
Max Act: 3.8809. Min Act: -0.1700
Data Index: 6975223 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1310. Min Range: -4.1310
Max Act: 3.8809. Min Act: -0.1700
Data Index: 1619749 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1310. Min Range: -4.1310
Max Act: 3.8809. Min Act: -0.1700
Data Index: 4644572 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1310. Min Range: -4.1310
Max Act: 3.8809. Min Act: -0.1700
Data Index: 6921728 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1310. Min Range: -4.1310
Max Act: 3.8809. Min Act: -0.1700
Data Index: 5313625 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1310. Min Range: -4.1310
Max Act: 3.8653. Min Act: -0.1700
Data Index: 8362434 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1310. Min Range: -4.1310
Max Act: 3.8653. Min Act: -0.1700
Data Index: 3804509 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1310. Min Range: -4.1310
Max Act: 3.8496. Min Act: -0.1700
Data Index: 4191258 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1310. Min Range: -4.1310
Max Act: 3.8496. Min Act: -0.1700
Data Index: 2503771 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1310. Min Range: -4.1310
Max Act: 3.8496. Min Act: -0.1700
Data Index: 1982592 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1310. Min Range: -4.1310
Max Act: 3.8496. Min Act: -0.1700
Data Index: 7295763 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19