Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1844 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.6558. Min Act: -0.1700
Data Index: 8449929 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.6209. Min Act: -0.1700
Data Index: 8615571 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.5510. Min Act: -0.1700
Data Index: 3160217 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.5510. Min Act: -0.1700
Data Index: 7250783 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.5685. Min Act: -0.1700
Data Index: 2655370 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.5510. Min Act: -0.1700
Data Index: 3857013 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.4984. Min Act: -0.1700
Data Index: 1528775 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.4984. Min Act: -0.1700
Data Index: 7406601 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.5160. Min Act: -0.1700
Data Index: 1292944 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.4721. Min Act: -0.1700
Data Index: 3651169 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.4808. Min Act: -0.1700
Data Index: 7397178 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.4721. Min Act: -0.1700
Data Index: 899629 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.4984. Min Act: -0.1700
Data Index: 980044 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.4808. Min Act: -0.1700
Data Index: 8764200 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.4808. Min Act: -0.1700
Data Index: 3750818 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.4721. Min Act: -0.1700
Data Index: 7716664 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.4721. Min Act: -0.1700
Data Index: 3377523 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.4721. Min Act: -0.1700
Data Index: 2888315 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.4721. Min Act: -0.1700
Data Index: 3655776 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6558. Min Range: -1.6558
Max Act: 1.4633. Min Act: -0.1700
Data Index: 3888297 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19