Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4242 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.9849. Min Act: -0.1700
Data Index: 4326326 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.9849. Min Act: -0.1700
Data Index: 4789945 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.9537. Min Act: -0.1700
Data Index: 3999446 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.9537. Min Act: -0.1700
Data Index: 6545036 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.8912. Min Act: -0.1700
Data Index: 5397226 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.8912. Min Act: -0.1700
Data Index: 8496021 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.8912. Min Act: -0.1700
Data Index: 4448418 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.8287. Min Act: -0.1700
Data Index: 6365968 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.8287. Min Act: -0.1700
Data Index: 1061673 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.7974. Min Act: -0.1700
Data Index: 8350235 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.7974. Min Act: -0.1700
Data Index: 2046308 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.7349. Min Act: -0.1700
Data Index: 7602078 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.7349. Min Act: -0.1700
Data Index: 8055051 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.7349. Min Act: -0.1700
Data Index: 7303082 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.7037. Min Act: -0.1700
Data Index: 542060 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.7037. Min Act: -0.1700
Data Index: 34589 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.6412. Min Act: -0.1700
Data Index: 6276524 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.6412. Min Act: -0.1700
Data Index: 2121895 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.6099. Min Act: -0.1700
Data Index: 8322154 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9849. Min Range: -5.9849
Max Act: 5.6412. Min Act: -0.1700
Data Index: 2051175 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19