Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.2610. Min Act: -0.1700
Data Index: 8344625 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.1985. Min Act: -0.1700
Data Index: 420597 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.1672. Min Act: -0.1700
Data Index: 5865635 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.1360. Min Act: -0.1700
Data Index: 6184837 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.1360. Min Act: -0.1700
Data Index: 4083594 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0735. Min Act: -0.1700
Data Index: 7098390 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0735. Min Act: -0.1700
Data Index: 1215354 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0735. Min Act: -0.1700
Data Index: 772177 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0735. Min Act: -0.1700
Data Index: 1646752 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0422. Min Act: -0.1700
Data Index: 101004 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0422. Min Act: -0.1700
Data Index: 3157531 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0422. Min Act: -0.1700
Data Index: 3520979 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2610. Min Range: -5.2610
Max Act: 5.0422. Min Act: -0.1700
Data Index: 1378208 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9485. Min Act: -0.1700
Data Index: 6519956 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9797. Min Act: -0.1700
Data Index: 2320724 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9797. Min Act: -0.1700
Data Index: 2021701 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9797. Min Act: -0.1700
Data Index: 2577683 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9797. Min Act: -0.1700
Data Index: 2457296 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9797. Min Act: -0.1700
Data Index: 4021038 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2610. Min Range: -5.2610
Max Act: 4.9485. Min Act: -0.1700
Data Index: 5626781 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19