Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3251 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.6797. Min Act: -0.1700
Data Index: 1838725 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.4922. Min Act: -0.1700
Data Index: 350003 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.4297. Min Act: -0.1700
Data Index: 7035531 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.3047. Min Act: -0.1700
Data Index: 1838738 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.3047. Min Act: -0.1700
Data Index: 4587960 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.2422. Min Act: -0.1700
Data Index: 2222884 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.2422. Min Act: -0.1700
Data Index: 8347527 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.1797. Min Act: -0.1700
Data Index: 1838727 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.1797. Min Act: -0.1700
Data Index: 1838731 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.1172. Min Act: -0.1700
Data Index: 1838732 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.1172. Min Act: -0.1700
Data Index: 8321318 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.1172. Min Act: -0.1700
Data Index: 2078965 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.0547. Min Act: -0.1700
Data Index: 1463736 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.0547. Min Act: -0.1699
Data Index: 8392238 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.0547. Min Act: -0.1700
Data Index: 8234112 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.0547. Min Act: -0.1700
Data Index: 2673482 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.0547. Min Act: -0.1700
Data Index: 3383932 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.0547. Min Act: -0.1700
Data Index: 5964539 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.0547. Min Act: -0.1700
Data Index: 1838730 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6797. Min Range: -9.6797
Max Act: 9.0547. Min Act: -0.1700
Data Index: 8300860 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19