Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4467 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.6758. Min Act: -0.1700
Data Index: 7289298 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.4883. Min Act: -0.1700
Data Index: 4119406 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.4883. Min Act: -0.1700
Data Index: 2495684 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.4258. Min Act: -0.1700
Data Index: 5216473 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.4258. Min Act: -0.1700
Data Index: 5956441 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.4258. Min Act: -0.1700
Data Index: 2968514 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.3633. Min Act: -0.1700
Data Index: 2597617 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.3633. Min Act: -0.1700
Data Index: 7650746 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.3008. Min Act: -0.1700
Data Index: 1480174 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.3008. Min Act: -0.1700
Data Index: 7202968 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.3008. Min Act: -0.1700
Data Index: 7068447 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.3008. Min Act: -0.1700
Data Index: 1113586 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.2383. Min Act: -0.1700
Data Index: 5722018 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.2383. Min Act: -0.1700
Data Index: 1862948 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.2383. Min Act: -0.1700
Data Index: 7229272 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.2383. Min Act: -0.1700
Data Index: 195534 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.1758. Min Act: -0.1700
Data Index: 6172980 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.1133. Min Act: -0.1700
Data Index: 6325638 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.1133. Min Act: -0.1700
Data Index: 7023287 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6758. Min Range: -8.6758
Max Act: 8.1133. Min Act: -0.1700
Data Index: 4116998 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19