Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.9290. Min Act: -0.1700
Data Index: 7102105 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.7103. Min Act: -0.1700
Data Index: 7786579 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.6478. Min Act: -0.1700
Data Index: 8502299 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.6165. Min Act: -0.1700
Data Index: 8581017 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.5853. Min Act: -0.1700
Data Index: 1060277 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.5228. Min Act: -0.1700
Data Index: 2299081 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.5540. Min Act: -0.1700
Data Index: 7719570 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.5228. Min Act: -0.1700
Data Index: 3612489 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.4603. Min Act: -0.1700
Data Index: 4329483 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.3978. Min Act: -0.1700
Data Index: 2150874 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.3978. Min Act: -0.1700
Data Index: 5609156 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.3665. Min Act: -0.1700
Data Index: 4356872 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.3353. Min Act: -0.1700
Data Index: 3895954 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.3353. Min Act: -0.1700
Data Index: 2442881 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.3353. Min Act: -0.1700
Data Index: 203676 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.3353. Min Act: -0.1700
Data Index: 5417091 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.3353. Min Act: -0.1700
Data Index: 5603879 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.3040. Min Act: -0.1700
Data Index: 5667458 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.3040. Min Act: -0.1700
Data Index: 2499196 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9290. Min Range: -5.9290
Max Act: 5.3040. Min Act: -0.1700
Data Index: 3926114 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19