Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2164 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1547. Min Range: -6.1547
Max Act: 6.1547. Min Act: -0.1700
Data Index: 3243538 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.9359. Min Act: -0.1700
Data Index: 2916322 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.8734. Min Act: -0.1700
Data Index: 3547133 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.8422. Min Act: -0.1700
Data Index: 7031795 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.7172. Min Act: -0.1700
Data Index: 2425832 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.6859. Min Act: -0.1700
Data Index: 224517 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.6234. Min Act: -0.1700
Data Index: 6636968 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.6234. Min Act: -0.1700
Data Index: 1476325 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.6234. Min Act: -0.1700
Data Index: 3587528 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.6234. Min Act: -0.1700
Data Index: 8702921 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.5922. Min Act: -0.1700
Data Index: 3017359 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.5609. Min Act: -0.1700
Data Index: 477203 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.5609. Min Act: -0.1700
Data Index: 3754657 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.5609. Min Act: -0.1700
Data Index: 8380925 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.4984. Min Act: -0.1700
Data Index: 2617812 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.4984. Min Act: -0.1700
Data Index: 6368769 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.5297. Min Act: -0.1700
Data Index: 2955298 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.4984. Min Act: -0.1700
Data Index: 8329988 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.4984. Min Act: -0.1700
Data Index: 862660 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1547. Min Range: -6.1547
Max Act: 5.4672. Min Act: -0.1700
Data Index: 7275263 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19