Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 396 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.6514. Min Act: -0.1700
Data Index: 8467479 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.6514. Min Act: -0.1700
Data Index: 6831993 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5576. Min Act: -0.1700
Data Index: 3050237 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5576. Min Act: -0.1700
Data Index: 4405673 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5576. Min Act: -0.1700
Data Index: 522868 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5264. Min Act: -0.1700
Data Index: 3986764 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.5264. Min Act: -0.1700
Data Index: 2172457 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.4951. Min Act: -0.1700
Data Index: 4112035 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.4326. Min Act: -0.1700
Data Index: 2403920 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.4014. Min Act: -0.1700
Data Index: 6535505 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.4014. Min Act: -0.1700
Data Index: 5475060 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.3701. Min Act: -0.1700
Data Index: 7061928 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.3701. Min Act: -0.1700
Data Index: 4931307 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.3701. Min Act: -0.1700
Data Index: 1294123 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.3701. Min Act: -0.1700
Data Index: 1088517 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.3076. Min Act: -0.1700
Data Index: 6188176 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.3389. Min Act: -0.1700
Data Index: 4405674 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.3076. Min Act: -0.1700
Data Index: 2464925 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.2764. Min Act: -0.1700
Data Index: 3644424 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6514. Min Range: -4.6514
Max Act: 4.2764. Min Act: -0.1700
Data Index: 400971 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19